ClawAudit verdict
feishu-security
An explicit security isolation layer for Feishu bots that reads owner identity from local config and environment variables to implement permission gating; file_read and credential_access capabilities directly serve the stated anti-hijacking and anti-injection security purpose.
⚠ 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.
Permission integrity
file_read
Findings (7)
Accesses sensitive system files
SKILL.md · code · /etc/passwd
Reads /proc/self/environ — dumps all environment variables
SKILL.md · code · /proc/self/environ
Accesses .ssh directory
SKILL.md · code · .ssh/
Accesses cloud provider credentials
SKILL.md · code · ~/.aws
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Possible prompt injection — attempts to redefine agent identity
SKILL.md · prose · downgraded · you are now
Sets world-executable permissions
install.sh · prose · downgraded · chmod 700
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
credential_accesscredential_storefile_read Is this flag fair?
Thanks — recorded.