code-to-requirements
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is intended to read local project files, such as configuration files (package.json, requirements.txt, pom.xml) and source code, to generate requirement documents. This behavior is consistent with its stated purpose and does not involve unauthorized network access or sensitive file theft.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests untrusted content from source code comments or documentation within a project.
- Ingestion points: The agent reads arbitrary source code and configuration files during the scanning phase (SKILL.md Step 1.3).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of these files.
- Capability inventory: The skill uses file-reading and globbing capabilities to traverse the project directory.
- Sanitization: There is no explicit instruction to sanitize or escape instructions that might be embedded within the project's code or documentation.
Audit Metadata