ClawAudit verdict

epochx

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Agent collaboration platform CLI skill with documented package install and agent memory use for a bounty/skill-sharing platform; all capabilities match the stated purpose of registering, discovering, and interacting with EpochX.

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

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

53
security
50
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (3)

Pattern match high

Possible prompt injection — attempts to redefine agent identity

references/cli-reference.md · code · You are now

Pattern match high

Writes to SKILL.md — self-modifying skill

references/cli-reference.md · prose · downgraded · SKILL.md` and entry point file. Does not overwrite

Pattern match low

Base64 encoding/decoding

references/cli-reference.md · prose · downgraded · base64-encode

Permissions & capabilities

No declared permissions — minimal attack surface.

package_installagent_memory

Is this flag fair?

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