ClawAudit verdict

onemind-skill

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

Accesses credentials AND makes external network calls

OneMind collective consensus platform skill using Supabase anonymous authentication; the API key in the content is a public Supabase anon key, and executionSink reflects documented API curl calls.

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.

23
security
30
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Pattern match high

Long base64 string (100+ chars) — likely obfuscated payload

TEST_REPORT_V2.md · code · eyJpc3MiOiJodHRwczovL2NjeXV4cnRya2xncGt6Y3J5enBqLnN1cGFiYXNlLmNvL2F1dGgvdjEiLCJz

Pattern match low

Popular HTTP library — network access

test_submit_ratings.sh · prose · downgraded · Got

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). 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_outcredential_access
Check another skill Browse the registry Auditing your own skills or configs? Use the API