Agent skill · Audited from source
Bernstein Agents
skill · sipyourdrink-ltd/bernsteinApache-2.0 licenceAudited 14 Oct 2026 · source 6ba64a7d2489
Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 6ba64a7d2489 and observed network access and no hard-coded secrets. The audit raised 5 findings, 0 critical or high. What it does: Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one.
Cite
Cite this page
ModelsAtlas. “Bernstein Agents (sipyourdrink-ltd/bernstein)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-agents
Trust audit
Audit 0.4.1 · source read 14 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkUndeclared4 observations, not in its own description
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | WARN | 4 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 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 (5)
MEDIUMNetwork egressnet.cli · scripts/agents.sh:20
DASH_JSON="$(curl -sf "${HEADERS[@]}" "$API/dashboard/data" 2>/dev/null || true)"- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.cli · scripts/agents.sh:32
curl -sf "${HEADERS[@]}" "$API/agents/$ID/logs?tail_bytes=4096" || echo '{"error": "Could not fetch logs"}' >&2- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.cli · scripts/agents.sh:36
curl -sf "${HEADERS[@]}" -X POST "$API/agents/$ID/kill" || echo '{"error": "Could not kill agent"}' >&2- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.raw_ip · scripts/agents.sh:6
API="${BERNSTEIN_API_URL:-http://127.0.0.1:8052}"- Why
- No further detail recorded for this rule.
- Fix
- —
INFOPrompt injectionscope.undeclared_network · <declared scope>
network use found in code, not declared in the description
- Why
- the description does not admit a capability the code has
- Fix
- declare network use in the description, or remove it
Audit 0.4.1 · source sha 6ba64a7d2489 · 14 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishersipyourdrink-ltd GitHub organizationOwner of the repository this skill is read from
- Source foldersipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-agentsThe exact folder we audited
- LicenceApache-2.0As the repository states it
- Commit pinned for this verdict6ba64a7d2489A 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: Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one.
--- name: bernstein-agents description: > Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one. --- # Bernstein Agent Management Inspect, monitor, and control active Bernstein agents. ## When to Use - User asks "what agents are running?" or "show me the agents" - User wants to see what a specific agent is working on - User says "kill that agent" or "stop the backend agent" - User asks "why is that agent stuck?" or wants to inspect agent output - User wants to see agent logs ## Instructions ### List agents 1. Run `scripts/agents.sh list` to get all active agents. 2. Present them clearly: ``` ## Active Agents (3) | Agent | Role | Model | Status | Task | Runtime | Cost | |-------|------|-------|--------|------|---------|------| | ses-a1b2 | backend | claude-sonnet-4 | alive | TASK-042: Fix auth | 4m 12s | $0.32 | | ses-c3d4 | qa | gpt-4.1 | alive | TASK-043: Write tests | 2m 45s | $0.18 | | ses-e5f6 | frontend | claude-sonnet-4 | stalled | TASK-044: Update UI | 8m 03s | $0.51 | ``` ### Inspect agent 3. To see what an agent is doing: `scripts/agents.sh logs <session_id>` 4. Show the last ~20 lines of output. ### Kill agent 5. To kill a stalled or misbehaving agent: `scripts/agents.sh kill <session_id>` 6. Confirm: "Agent ses-e5f6 terminated. Task TASK-044 returned to open queue." ### Stall detection 7. If any agent shows `stalled` status, proactively suggest killing it. 8. An agent is stalled if it hasn't sent a heartbeat in >60 seconds.
Excerpt, first 1,630 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 6ba64a7
git clone https://github.com/sipyourdrink-ltd/bernstein git -C bernstein checkout 6ba64a7d2489
The author documents no install command, so this uses the repository directly. Our verdict covers commit 6ba64a7d2489 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- !CAUTION B 89 / 100
first audit · source
6ba64a7d2489
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-agents/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
sipyourdrink-ltd/bernstein
Evaluate proposals - feasibility, engineering payoff, risk.
sipyourdrink-ltd/bernstein
System design - module boundaries, API contracts, ADRs.
sipyourdrink-ltd/bernstein
Python server code, APIs, async, strict typing.
sipyourdrink-ltd/bernstein
Show active alerts from Bernstein - failed tasks, stalled agents, budget warnings, blocked tasks needing human intervention. Use when the user asks about problems, errors, warnings, or what needs attention.
sipyourdrink-ltd/bernstein
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.
sipyourdrink-ltd/bernstein
Show detailed cost breakdown and budget status for the Bernstein orchestrator. Use when the user asks about spending, budget, cost per model, cost per agent, or wants a cost projection.
Add this badge to your README
[](https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-agents/)
<a href="https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-agents/"><img src="https://modelsatlas.com/skills/sipyourdrink-ltd/bernstein-agents/badge.svg" alt="ModelsAtlas: CAUTION B"></a>
Questions about Bernstein Agents
What does the Bernstein Agents skill do?
Is Bernstein Agents safe to install?
What can Bernstein Agents access on my machine?
How current is this page?
Sources
- github.com/sipyourdrink-ltd/bernstein/tree/main/packages/cursor- — the audited source at commit 6ba64a7d2489 and every finding aboveObserved · 14 Oct 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 Bernstein Agents skill do?
- Is Bernstein Agents safe to install?
- What can Bernstein Agents access on my machine?