do-status
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from local markdown files to generate a summary report, creating a potential surface for indirect instructions if the files are modified by an external actor.
- Ingestion points: The procedures in
SKILL.md(Steps 2, 3, and 3B) read content from./prds/prd-[feature-slug]/tasks/tasks.mdand various review/QA report files. - Boundary markers: No delimiters or warnings are used to isolate the data read from these files from the agent's instructions.
- Capability inventory: The skill is strictly read-only and does not possess capabilities for file writing, network access, or command execution, which minimizes the risk of a successful exploit.
- Sanitization: The skill does not apply sanitization or validation to the text read from the project files before generating the report.
Audit Metadata