Caveat verdict

agent-emacs

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

Receives external input AND uses eval

A persistent Emacs daemon environment for AI agents using well-known tools (emacsclient, TRAMP, Magit); dynamic_eval refers to standard Emacs Lisp REPL usage for accuracy which is the documented and expected purpose of this tool.

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.

58
security
80
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)

LLM01 · LLM05 · ASI01 · ASI05

Findings (1)

Pattern match low

References agent memory files

references/agent-workflows.md · prose · downgraded · MEMORY.md

Permissions & capabilities

No declared permissions — minimal attack surface.

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