verification
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scans local project files (e.g., source code, configuration files like package.json, pyproject.toml) to perform its analysis. This creates an attack surface where untrusted data from the analyzed project could attempt to influence the agent's behavior during report generation.
- Ingestion points: Local project files, imports, and framework configurations scanned during Step 1.
- Boundary markers: The skill does not explicitly define delimiters or specific 'ignore' instructions for the data it processes.
- Capability inventory: The skill has the capability to create directories (mkdir) and write markdown files to the local file system (reports/verification/).
- Sanitization: No specific sanitization or escaping of the ingested code content is mentioned before it is included in the final report.
- [SAFE]: The skill is a standard developer tool that performs all analysis locally on the user's machine. It does not attempt to exfiltrate data, use obfuscation, or execute remote code. All identified behaviors (file reading and report writing) are consistent with its primary purpose as an auditing tool.
Audit Metadata