edge-case-hunter
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it ingests and processes source code provided by the user. Malicious instructions embedded in comments or strings within the analyzed code could potentially influence the agent's behavior during the review process.
- Ingestion points: The skill reads source code from local directories, files, or git branches provided as input.
- Boundary markers: No delimiters or explicit instructions are provided to the agent to distinguish between its core instructions and the untrusted data being analyzed.
- Capability inventory: The skill has the ability to read from the file system and generate a markdown report file.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the ingested code content to prevent command or prompt injection.
- [NO_CODE]: This skill consists entirely of configuration and markdown instructions; it does not include any executable binary or script files.
Audit Metadata