Caveat verdict

academic-pipeline

ars-academic-pipeline

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

A multi-stage academic writing orchestrator delegating tasks between internal skill stages; no external data exfiltration and executionSinkDetected reflects normal pipeline orchestration.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

38
security
90
transparency
70
maintenance

Findings (4)

Pattern match critical

Possible hardcoded credential

shared/cross_model_verification.md · code · API_KEY="sk-your-key-here

Pattern match high

Instructs covert action — may act without user awareness

references/literature_corpus_consumers.md · code · silently

Pattern match medium

Accesses shell history/config

shared/cross_model_verification.md · prose · downgraded · ~/.zshrc

Pattern match low

Popular HTTP library — network access

references/ai_research_failure_modes.md · prose · downgraded · got

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API