ClawAudit verdict
slack-personal
The skill wraps the slk CLI to read/send Slack messages using the user's own session tokens; all operations are transparently documented and scoped to the user's own Slack workspace.
⚠ 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.
Findings (5)
Accesses system credential store
AGENTS.md · code · Keychain
Writes to SKILL.md — self-modifying skill
AGENTS.md · prose · downgraded · SKILL.md** — Add to the commands list under the appropriate section (Read/Activi
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
References agent configuration files
AGENTS.md · code · CLAUDE.md
References child_process — can spawn system processes
README.md · prose · downgraded · child_process
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
Is this flag fair?
Thanks — recorded.