ClawAudit verdict

agent-memory

memory-and-context-engineering

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

Agent memory infrastructure skill using local Python packages for in-process context management with no outbound data exfiltration.

⚠ 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.

30
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match critical

Possible hardcoded credential

references/best_practices.md · code · password="encryption_key

Pattern match high

Pipe to python — executes piped content as Python code

references/context_compaction_rules.md · prose · downgraded · | Python

Pattern match medium

Python shutil file operation — copies/moves/deletes files

references/best_practices.md · code · shutil.copy(

Pattern match low

Python threading.Timer — deferred execution

scripts/batched_writer.py · prose · downgraded · threading.Timer(

Pattern match low

Python os.getenv — reads environment variable

scripts/credential_manager.py · prose · downgraded · os.getenv(

Permissions & capabilities

No declared permissions — minimal attack surface.

package_install

Is this flag fair?

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