Agent Reputation Checker

ReviewAudited by ClawScan on May 10, 2026.

Overview

This skill should be reviewed before use because it uses bundled and local platform credentials, and some checks appear to score a fixed or self account instead of the agent you asked about.

Before installing, treat the output as untrusted for payment or safety decisions until the skill removes hardcoded credentials, declares any local credential use, and verifies that every platform lookup actually checks the agent name you provide.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The trust score could be based on the wrong account, which may mislead users making payment or collaboration decisions.

Why it was flagged

The code shows some platform checks using a fixed or self account rather than the user-supplied agent name, despite the skill being presented as a reputation check for a named agent.

Skill content
body={"agent_id": "bro-agent", "api_key": COLONY_API_KEY} ... "https://thecolony.cc/api/v1/agents/me" ... "use /agents/me for self-check"
Recommendation

Only rely on the score after the skill uses target-specific lookups for every platform, or clearly labels self-checks and excludes them from the target agent's score.

What this means

Requests may run under unknown bundled accounts or shared API quotas, and users cannot scope, rotate, or revoke those credentials themselves.

Why it was flagged

The script contains literal provider API credentials while the registry metadata declares no primary credential or required environment variables.

Skill content
COLONY_API_KEY = "col_..."; CLAWK_API_KEY = "clawk_..."; UGIG_API_KEY = "ugig_live_..."; RIDGELINE_API_KEY = "rdg_..."
Recommendation

Remove hardcoded API keys and require user-provided, least-privilege credentials through declared environment variables or configuration.

What this means

If a Moltbook credential exists on the machine, the skill can use that account credential during a reputation check without a clear metadata-level permission boundary.

Why it was flagged

The script reads a local Moltbook API key and uses it for authenticated requests, even though the registry metadata lists no required config paths or credentials.

Skill content
p = Path.home() / ".config" / "moltbook" / "credentials.json" ... headers={"X-API-Key": key}
Recommendation

Declare the credential and config path in metadata, ask the user before using local account credentials, and make clear exactly which account data is accessed.