docgen
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because its primary function is to read and analyze arbitrary source code files. Malicious instructions could be embedded within the files (e.g., inside comments or strings) to manipulate the agent's behavior during the analysis phase.
- Ingestion points: Files are read fully during Step 3 ('Analyze Each File') of the workflow as defined in
SKILL.mdandreferences/docgen-strategy.md. - Boundary markers: The skill lacks instructions for the agent to use delimiters or to specifically ignore natural language instructions found within the source code data.
- Capability inventory: The skill requires read access to all files within the user-defined scope on the local filesystem.
- Sanitization: There is no validation or sanitization of the input file content to identify or strip potential injection strings before processing.
Audit Metadata