Agent skill · Audited from source
compress
skill · juliusbrussee/cavemanApache-2.0 licenceAudited 14 Nov 2026 · source 4b1590a946a0
Is it safe? No — BLOCK, grade F (30/100). We read this skill's source at commit 4b1590a946a0 and observed filesystem, network and shell access and a hard-coded secret (see the findings). The audit raised 25 findings, 11 critical or high. What it does: When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main…
Cite
Cite this page
ModelsAtlas. “compress (juliusbrussee/caveman)”. Retrieved 14 Nov 2026. https://modelsatlas.com/skills/juliusbrussee/compress
Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 11 critical or high findings, starting with “Inventory / provenance” in shared/platform/redact/payload.go. Do not install it without reading them.
2 skills are called “compress”. You are viewing juliusbrussee/caveman. 2 of them are BLOCK.
- juliusbrussee/caveman★ 120k✕BLOCK
- juliusbrussee/caveman★ 119k✕BLOCK
Trust audit
Audit 0.4.1 · source read 14 Nov 2026
BLOCK means the audit found something that could harm you or your machine. Grade F is shared by 129 of 18,389 audited skills.
What the source does
- FilesystemDeclared7 observations
- NetworkDeclared12 observations
- ShellDeclared10 observations
- DependenciesNot pinnedSome versions float
- SecretsFoundSee the findings; values are never shown
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | FAIL | 6 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | FAIL | 18 |
L2 Instructions | Prompt injection, authority framing, hidden directives | FAIL | 1 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (25)
HIGHInventory / provenanceinv.suspicious_name · shared/platform/redact/payload.go
payload.go
- Why
- member named after an attack tool
- Fix
- remove or justify
HIGHCode injectioncode.eval_exec · browse/cdp.go:246
func (d *CDPDriver) Eval(ctx context.Context, expression string) (any, error) {- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · browse/cmd/caveman-browse/main.go:509
func (nilDriver) Eval(context.Context, string) (any, error) { return nil, context.Canceled }- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · browse/session.go:34
Eval(ctx context.Context, expression string) (any, error)
- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · engine/ccr/store_sqlite.go:201
Exec(query string, args ...any) (sql.Result, error)
- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHNetwork egressnet.metadata_ip · shared/platform/awscreds/awscreds.go:64
defaultIMDSBase = "http://169.254.169.254"
- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
HIGHNetwork egressnet.metadata_ip · shared/platform/awscreds/awscreds.go:467
netip.MustParseAddr("169.254.169.254"),- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
HIGHNetwork egressnet.metadata_ip · shared/platform/awscreds/awscreds.go:531
return fmt.Errorf("awscreds: refusing plaintext IMDS endpoint at host %q (allowed: loopback, 169.254.169.254, fd00:ec2::254)", u.Hostname())- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
HIGHNetwork egressnet.tls_off · shared/platform/postgresconfig/postgresconfig.go:74
config.ConnConfig.TLSConfig.InsecureSkipVerify = false
- Why
- certificate verification is disabled
- Fix
- leave verification on
HIGHNetwork egressnet.tls_off · shared/platform/postgresconfig/postgresconfig.go:81
fallback.TLSConfig.InsecureSkipVerify = false
- Why
- certificate verification is disabled
- Fix
- leave verification on
HIGHPrompt injectionprompt.credential_read · plugins/caveman/skills/caveman-compress/SKILL.md:13
> **Data leaves the machine.** Compression sends the file's full text to the model provider that `scripts/compress.py` is configured for: the `claude` CLI, the Anthropic API, or an OpenAI-compatible e
- Why
- asks the agent to read credentials
- Fix
- —
MEDIUMInventory / provenanceinv.binary · dist/caveman.skill
caveman.skill
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · engine/pixel/assets/atlas-codepoints.bin.gz
atlas-codepoints.bin.gz
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · engine/pixel/assets/atlas-offsets.bin.gz
atlas-offsets.bin.gz
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · engine/pixel/assets/atlas-pixels.bin.gz
atlas-pixels.bin.gz
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · engine/pixel/assets/atlas-wideflags.bin.gz
atlas-wideflags.bin.gz
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
MEDIUMCode injectioncode.dynamic_import · packages/middleware/python/caveman_middleware/_httpx2.py:28
http = importlib.import_module(name)
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMCode injectioncode.dynamic_import · packages/middleware/python/caveman_middleware/llama_index.py:68
if isinstance(model, getattr(importlib.import_module(module), name)):
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMCode injectioncode.dynamic_import · packages/middleware/python/caveman_middleware/pydantic_ai.py:66
if isinstance(model, getattr(importlib.import_module(module), name)):
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMInsecure cryptocrypto.weak_random · evals/snapshots/reminder.json:28
"That's React's default behavior. When a parent re-renders, React re-renders every child it renders, whether or not the child's props changed. React doesn't compare props unless you ask it to.\n\n**To
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · proxy/cmd/caveman-proxy/main.go:475
func withKeepalive(next http.Handler, beacon func()) http.Handler {- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · proxy/cmd/caveman-proxy/main.go:478
beacon()
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.raw_ip · .blocks/release-smoke.py:108
gateway = f"http://127.0.0.1:{port}"- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMObfuscation / stealthobf.base64_blob · engine/pixel/testdata/transform_anthropic/early_history_only.expected.json:17
"data": "iVBORw0KGgoAAAANSUhEUgAABiAAAALQCAIAAACWoC/QAAAxF0lEQVR4nO3dUW7kRrJAUS3C3/YevAZhtlRemPdXr0GCxchIMquolNohvXNhDHiSKTYlNQaDGLL8dpckSZIkSZImevuvb0CSJEmSJEnfOwMmSZIkSZIkTWXAJEmSJEmSpKl+34Dpj3/+fnr
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMObfuscation / stealthobf.base64_blob · engine/pixel/testdata/transform_anthropic/early_history_only.expected.json:25
"data": "iVBORw0KGgoAAAANSUhEUgAABiAAAADQCAIAAAABPz75AAAOmElEQVR4nO3dUXLjNhZAUS0i3+k9ZA2ubElZWPan6SKLIvAAgqKh7jx7zq354AFhmrJTXdVvRPXtIUmSJEmSJE10+69vQJIkSZIkSV87AyZJkiRJkiRNZcAkSZIkSZKkqQyYJEmSJEmSNJU
- Why
- No further detail recorded for this rule.
- Fix
- —
Audit 0.4.1 · source sha 4b1590a946a0 · 14 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherjuliusbrussee GitHub userOwner of the repository this skill is read from
- Source folderjuliusbrussee/cavemanThe exact folder we audited
- LicenceApache-2.0As the repository states it
- Commit pinned for this verdict4b1590a946a0A new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main…
--- name: cavecrew description: > When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer. --- Cavecrew = three subagent presets that answer in ultracave voice (tool runs: one status line in, one out; nothing between routine calls). Same job as Anthropic defaults (`Explore`, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation. ## When to use cavecrew vs alternatives | Task | Use | |---|---| | "Where is X defined / what calls Y / list uses of Z" | `cavecrew-investigator` | | Same but you also want suggestions/architecture commentary | `Explore` (vanilla) | | Surgical edit, ≤2 files, scope obvious | `cavecrew-builder` | | New feature / 3+ files / cross-cutting refactor | Main thread, or `feature-dev:code-architect` if installed | | Review diff, branch, or file for bugs | `cavecrew-reviewer` | | Deep code review with rationale + alternatives | `Code Reviewer` (vanilla) if installed, else main thread | | One-line answer you already know | Main thread, no subagent | Rule of thumb: **if you'd want the subagent's output in 1/3 the tokens, pick cavecrew. If you'd want prose, pick vanilla.** ## Why this exists (the real win) Subagent tool results get injected into main context verbatim. A vanilla `Explore` that returns 2k tokens of prose costs 2k tokens of main-context budget every time. The same finding from `cavecrew-investigator` comes back as a compressed `path:line` table instead. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task. ## Output contracts What main thread can rely on per agent: **`cavecrew-investigator`** ``` <Header>: - path:line — `symbol` — short note totals: <counts>. ``` Or `No match.` Always file-path-first, line-number-attached, backticked symbols. Safe to grep with `path:\d+`. **`cavecrew-builder`** ``` <path:line-range> — <change ≤10 words>. verified: <re-read OK | mismatch @ path:line>. ``` Or one of: `too-big.` / `needs-confirm.` / `ambiguous.` / `regressed.` (terminal first token). **`cavecrew-reviewer`** ``` path:line: <emoji> <severity>: <problem>. <fix>. totals: N🔴 N🟡 N🔵 N❓ ``` Or `No issues.` Findings sorted file → line ascending. ## Chaining patterns **Locate → fix → verify** (most common): 1. `cavecrew-investigator` returns site list. 2. Main thread picks 1-2 sites, hands paths to `cavecrew-builder`. 3. `cavecrew-reviewer` audits the diff. **Parallel scout** (when investigation is broad): Spawn 2-3 `cavecrew-investigator` calls in one message (different angles: defs vs callers vs tests). Aggregate in main thread. **Single-shot edit** (when site is already known): Skip investigator. Hand exact path:line to `cavecrew-builder` directly. ## What NOT to do - Don't accept or reject a subagent's absence claim (`No match.`, `No issues.`, "section missing", "unchanged") without one targeted check of the relevant file, search scope, or diff. Check cited line numbers are within the file before acting. - Don't use `cavecrew-builder` when you don't already know the file. Spawn investigator first or main thread will eat tokens passing context. - Don't chain `cavecrew-investigator → cavecrew-builder` for a 5-file refactor. Builder will return `too-big.` and you'll have wasted a turn. - Don't ask `cavecrew-reviewer` for "general feedback" — it returns findings only, no architecture opinions. Use `Code Reviewer` for that when installed. - Don't expect prose. Cavecrew output is structured, sometimes terse to the point of cryptic. If a human will read it directly, paraphrase. ## Auto-clarity (inherited) Subagents drop caveman → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume caveman after.
Excerpt, first 3,990 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 4b1590a
npx skills add JuliusBrussee/caveman -a kiro-cli -g npx skills add JuliusBrussee/caveman -a codex --copy git clone https://github.com/JuliusBrussee/caveman.git npx skills add JuliusBrussee/caveman -g npx skills add JuliusBrussee/caveman --skill caveman npm install --ignore-scripts --no-audit --no-fund --no-package-lock --prefix packages/cli
git clone https://github.com/juliusbrussee/caveman git -C caveman checkout 4b1590a946a0
Commands as the repository documents them: shown, never run by us. Our verdict covers commit 4b1590a946a0 only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| Claude Code | Mentioned in its text, not tested | Skills for Claude Code · About Claude Code |
| Claude Desktop | Mentioned in its text, not tested | Skills for Claude Desktop · About Claude Desktop |
| Codex | Mentioned in its text, not tested | Skills for Codex · About Codex |
| GitHub Copilot | Mentioned in its text, not tested | Skills for GitHub Copilot · About GitHub Copilot |
| Cursor | Mentioned in its text, not tested | Skills for Cursor · About Cursor |
| Gemini CLI | Mentioned in its text, not tested | Skills for Gemini CLI · About Gemini CLI |
| OpenClaw | Mentioned in its text, not tested | Skills for OpenClaw · About OpenClaw |
| Windsurf | Mentioned in its text, not tested | Skills for Windsurf · About Windsurf |
Audit history
Every audit, every source change
- ✕BLOCK F 30 / 100
first audit · source
4b1590a946a0
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/juliusbrussee/compress/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
juliusbrussee/caveman
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its…
juliusbrussee/caveman
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
juliusbrussee/caveman
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.
juliusbrussee/caveman
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
juliusbrussee/caveman
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
juliusbrussee/caveman
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
Add this badge to your README
[](https://modelsatlas.com/skills/juliusbrussee/compress/)
<a href="https://modelsatlas.com/skills/juliusbrussee/compress/"><img src="https://modelsatlas.com/skills/juliusbrussee/compress/badge.svg" alt="ModelsAtlas: BLOCK F"></a>
Questions about compress
What does the compress skill do?
Is compress safe to install?
What can compress access on my machine?
Which assistants does compress work with?
How current is this page?
Sources
- github.com/juliusbrussee/caveman — the audited source at commit 4b1590a946a0 and every finding aboveObserved · 14 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the compress skill do?
- Is compress safe to install?
- What can compress access on my machine?