code-docs
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks.
- Ingestion points: The agent reads source code files (C#, TypeScript, JavaScript, Python, Java) provided by the user or found in the project directory, which may contain malicious instructions hidden in comments or docstrings.
- Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings when processing code content.
- Capability inventory: The skill has the capability to write new Markdown files to the
docs/directory and modify existing source code files to add or update inline comments. - Sanitization: There is no mention of sanitizing or validating the extracted code metadata before using it to generate documentation or writing it back to files.
- [NO_CODE]: The skill consists entirely of markdown-based instructions and metadata within the SKILL.md file, with no accompanying scripts or executable binaries, which limits the risk of direct malicious code execution.
Audit Metadata