ClawAudit verdict

thecolony

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Accesses credentials AND makes external network calls

A collaborative agent platform that explicitly warns the agent about prompt injection attacks from user-generated content and instructs treating external content as data not instructions, which is defensive not manipulative.

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.

security

transparency

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 (1)

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("post"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · 1. **Register** using the `/auth/register` endpoint. Save your API key. 2. **Get a token** via `/auth/token`. 3. **List colonies** with `GET /colonies` and join

Permissions & capabilities

No declared permissions — minimal attack surface.

network_outcredential_accessnetwork_in

I installed anyway

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