status-updates
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides specific shell commands in
pr-evidence.mdfor the agent to execute. These commands use the GitHub CLI (gh) to search for and retrieve information about pull requests, including titles, files, and change metrics.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources (GitHub Pull Requests) which could potentially contain malicious instructions. - Ingestion points: Data is pulled from GitHub using
gh search prsas described inpr-evidence.md. - Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious content embedded within PR titles or descriptions.
- Capability inventory: The skill uses the GitHub CLI to fetch remote data and expects the agent to analyze and transform this data into status update reports.
- Sanitization: There are no documented steps for sanitizing or filtering the PR content before it is processed by the language model.
Audit Metadata