ClawAudit verdict
local-self-healing-machine-learning
Local machine learning skill for agent error correction explicitly asserting no telemetry, no fingerprinting, and no network calls; the skill description is consistent with a self-contained local learning loop with no contradicting evidence.
⚠ 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
network_out
Findings (12)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl -fsSL https://ollama.com/install.sh | sh
Pipe to sh — executes piped content as shell commands
SKILL.md · code · | sh
Possible hardcoded credential
test/sanitize.test.js · prose · downgraded · PASSWORD: "hunter2xyz
Recursive delete from root or home — destructive command
test/skillDistiller.test.js · prose · downgraded · rm -rf /
References child_process — can spawn system processes
scripts/generate_history.js · prose · downgraded · child_process
Uses spawn() — can execute external programs
index.js · prose · downgraded · spawn(
Uses exec() — may execute shell commands
src/evolve.js · prose · downgraded · exec(
Instructs covert action — may act without user awareness
src/evolve.js · prose · downgraded · silently
Accesses .ssh directory
test/sanitize.test.js · prose · downgraded · .ssh/
Node http/https module — low-level network access
dashboard/server.js · prose · downgraded · require('http')
References agent memory files
src/evolve.js · prose · downgraded · MEMORY.md
Popular HTTP library — network access
test/signals.test.js · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.
network_out Is this flag fair?
Thanks — recorded.