prd-update-progress
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard git utilities including
git log,git diff,git add, andgit committo correlate implementation work with PRD requirements. These actions are limited to the project repository and align with the skill's primary function of documentation synchronization. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from git history and code changes, creating a potential surface for indirect prompt injection.
- Ingestion points: Commit messages and file differences obtained via git tools (Step 2).
- Boundary markers: The skill provides a structured process for evaluation but does not specify delimiters or instructions to ignore potential commands embedded within commit messages.
- Capability inventory: The agent has the ability to execute shell commands (
git) and modify files in theprds/directory. - Sanitization: There is no evidence of filtering or sanitization of the content retrieved from git logs before it is processed by the agent.
Audit Metadata