ClawAudit verdict
scry
The skill uses a broad capability set to research topics across multiple sources, which may be excessive for its 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
agent_memory
Findings (6)
subprocess execution — runs system commands from Python
scripts/benchmark.py · prose · downgraded · subprocess.run(
Uses exec() — may execute shell commands
vendor/bird-search/lib/runtime-query-ids.js · prose · downgraded · exec(
Python os.environ.get — reads environment variable
scripts/lib/env.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/lib/http.py · prose · downgraded · urllib.request
importlib.import_module — dynamic module loading
scripts/lib/source_registry.py · prose · downgraded · importlib.import_module(
Popular HTTP library — network access
scripts/lib/sources/youtube.py · prose · downgraded · got
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.
agent_memory Is this flag fair?
Thanks — recorded.