logic-lens
Warn
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: MEDIUMPROMPT_INJECTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes untrusted source code, which serves as an ingestion point for indirect prompt injection. Maliciously crafted code could contain instructions that influence the agent's behavior during the review process. \n
- Ingestion points: Processes any user-provided source code files as part of the review tool's functionality. \n
- Boundary markers: There are no defined delimiters or specific instructions to help the agent isolate the code content from potentially malicious embedded instructions. \n
- Capability inventory: The skill uses the agent's reasoning capabilities to identify bugs and security risks and suggest fixes. \n
- Sanitization: No sanitization or escaping of the ingested code content is specified. \n- [EXTERNAL_DOWNLOADS]: The documentation suggests installing via
npx agentic-awesome-skills. This involves fetching a package from an unverified external NPM registry that is not associated with a trusted vendor. \n- [REMOTE_CODE_EXECUTION]: Usingnpxto install the skill results in the immediate execution of downloaded code from the unverifiedagentic-awesome-skillspackage, which is a significant supply chain risk.
Audit Metadata