ClawAudit verdict
ClawText Ingest
clawtext-ingest
The skill ingests external data sources (Discord, files, URLs, JSON) into structured agent memories with SHA1 deduplication; all described operations match the stated memory ingestion purpose and the credential access is to the ClawText/Discord APIs.
⚠ 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
credential_access
package_install
Findings (6)
Possible hardcoded credential
API_REFERENCE.md · code · TOKEN="your_token
References child_process — can spawn system processes
AGENT_GUIDE.md · code · child_process
Instructs covert action — may act without user awareness
ENHANCEMENT_REVIEW.md · code · silently
Accesses process.env — reads environment variables
SKILL.md · code
Accesses sensitive environment variables
SKILL.md · code · process.env.DISCORD_TOKEN
References agent memory files
AGENT_GUIDE.md · code · daily-notes
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
No declared permissions — minimal attack surface.
package_installcredential_access Is this flag fair?
Thanks — recorded.