ClawAudit verdict
self-improving-compound
Structured agent memory system using local SQLite and markdown files; operates locally within workspace directories with no network 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.
Permission integrity
package_install
Findings (8)
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
References agent memory files
SKILL.md · frontmatter · MEMORY.md
Instructs covert action — may act without user awareness
scripts/test_evals.py · prose · downgraded · silently
Popular HTTP library — network access
corrections.md · code · got
subprocess execution — runs system commands from Python
scripts/learning-audit.py · prose · downgraded · subprocess.run(
References agent configuration files
SKILL.md · prose · downgraded · CLAUDE.md
Python os.environ.get — reads environment variable
scripts/learning-audit.py · prose · downgraded · os.environ.get(
Python shutil file operation — copies/moves/deletes files
scripts/test_evals.py · prose · downgraded · shutil.rmtree(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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_install Is this flag fair?
Thanks — recorded.