Caveat verdict
context-compression
context-compression-claude-code-custom
This skill implements a tiered conversation compression strategy that writes local memory files; the claim that it was reverse-engineered from Claude Code internals is informational context, not manipulation, and the skill itself performs only local file writes.
⚠ 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.
Findings (2)
Pipe to python — executes piped content as Python code
setup-hook.md · code · | python3
Popular HTTP library — network access
SKILL.md · prose · downgraded · got
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.