pr-triage-report
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Command Execution: The skill utilizes the GitHub CLI (gh) and local scripting environments (PowerShell or Python) to fetch and process repository data. This is a standard and expected pattern for DevOps automation tasks, relying on the agent's local environment for data transformation.
- Indirect Prompt Injection: The skill processes external, untrusted content such as pull request titles and comments to compute triage metrics (e.g., identifying unresolved review threads). While this represents a potential data ingestion surface common to repository management tools, the skill is scoped to reporting and does not perform automated modifications or sensitive operations based on this content.
- Data Handling: The skill prioritizes authoritative GitHub API sources and structured data over user interface summaries, which helps ensure the integrity of the generated report and reduces the risk of misinterpretation.
Audit Metadata