Conf SearchSAFE
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
Overview
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
d8030f4516acOBSERVED · 2026-10-12Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| codex | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: conf-search description: "Search papers from top AI/ML conferences" --- # conf-search Search for papers from top venues. ## Usage ``` Claude Code: /conf-search --venue CVPR2025 --query "gesture generation" Claude Code: /conf-search --venue NeurIPS2025 --query "diffusion models" Codex: $conf-search ``` ## Supported Venues CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI, IJCAI, ACL, EMNLP, NAACL, SIGGRAPH, and more. ## Behavior 1. Parse venue and query from user input 2. Search via Semantic Scholar API with venue filter 3. Sort by relevance and citation count 4. Present results with title, authors, abstract snippet, citation count 5. Offer to do deep analysis on any paper of interest
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
d8030f4516acfull audit observations/trust-audit/skill/xiangyue-zhang__conf-search.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | d8030f4516ac | SAFE | B | 89 | first audit |
Questions
What does the Conf Search skill do?
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
Is Conf Search safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Conf Search access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Conf Search work with?
Its documentation mentions claude-code and codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (d8030f4516ac), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.