Caveat verdict

agentictrade

🟢 Trusted

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

The skill appears to be a marketplace connector for AI agents to sell and buy services autonomously using USDC, with no malicious or deceptive behavior detected.

⚠ 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.

security

transparency

maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

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. Make sure you have an HTTPS endpoint that accepts POST requests with JSON body and returns JSON. 2. Register it: ``` curl -X POST https://agentictrade.io/api

Pattern match medium

Possible prompt injection — attempts to redefine agent identity

SKILL.md · prose · downgraded · You are now

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: AGENTICTRADE_API_KEY). Requires 1 system binary. (1 elevated: curl).

network_outpackage_install

Is this flag fair?

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