eg-change-documentation-rigor
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically
git ls-files | grep -i -E 'pull_request_template|merge_request_templates', to identify existing documentation templates within a repository. This is a standard read-only development operation. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as code diffs, dependency version strings, and user-provided descriptions of changes to generate documentation.
- Ingestion points: Processes change descriptions, diffs, and dependency bump logs provided in the agent's context.
- Boundary markers: The instructions do not specify the use of delimiters or specific blocks to isolate user-provided change data from the generation instructions.
- Capability inventory: The skill uses command execution (
git) and generates structured text intended for version control systems. - Sanitization: No explicit sanitization or filtering of the ingested change descriptions is mentioned to prevent instructions embedded within the code or descriptions from influencing the agent's behavior.
Audit Metadata