project-discover-products-ops-dod
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external project source files (linked via
source_filesmetadata) and existing markdown documentation to generate and maintain a project knowledge base in the.aidlc/project/directory. This creates an attack surface for indirect prompt injection where malicious instructions embedded in source code could attempt to manipulate the generated documentation or influence the agent's understanding of the project. - Ingestion points: Reads project source files and existing documentation located in
.aidlc/project/components/. - Boundary markers: The instructions do not mandate the use of delimiters or specific 'ignore embedded instructions' prompts when interpolating content from source code into markdown templates.
- Capability inventory: The skill performs file system read and write operations restricted to the local project documentation directory.
- Sanitization: There is no specified logic for sanitizing or escaping content extracted from source files before it is written to the documentation pages.
Audit Metadata