Caveat verdict
mathematical-audit-skills
Fetches from network AND uses eval/Function
Content explicitly and repeatedly states read-only file access, no network, no dynamic execution despite capability flags; it is a static mathematical analysis tool for code auditing.
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.
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.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Reads files AND uses eval/Function — may execute locally stored payloads
LLM05 · LLM06 · ASI05
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Executes processes AND makes external network calls — may exfiltrate command output
LLM02 · LLM06 · ASI03
Permission integrity
network_out
Findings (4)
Uses eval() — can execute arbitrary code
SKILL.md · code · eval(
Uses exec() — may execute shell commands
SKILL.md · code · exec(
Writes to SKILL.md — self-modifying skill
CHANGELOG.md · prose · downgraded · SKILL.md "No file write
References agent memory files
CHANGELOG.md · prose · downgraded · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outfile_readprocess_execdynamic_eval Thanks — recorded.