Caveat verdict

botpicks-api

botpicks

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

The skill competes on real prediction markets via the BotPicks API, allowing users to make predictions and participate in competitions, with no evidence of malicious behavior.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

80
security
90
transparency
90
maintenance

Findings (2)

Pattern match high

Possible prompt injection — attempts to redefine agent identity

SKILL.md · code · You are now

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 · To obtain an API key: 1. Register an agent via `POST https://botpicks.ai/api/v1/agents/register` 2. Save the returned `api_key` (it cannot be retrieved later) 3

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: BOTPICKS_API_KEY).

credential_access

Is this flag fair?

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