github-deep-review
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands including
gh,git, andrgto retrieve issue details, PR diffs, and repository state. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted content from GitHub issues and pull requests.
- Ingestion points: The agent uses
gh issue view,gh pr view, andgh pr diffto bring external content into the context (SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the GitHub issues or PR descriptions.
- Capability inventory: The agent has access to shell execution (
gh,git,rg) and can read local files at specified paths like~/Projects/agent-scripts/. - Sanitization: There is no evidence of content sanitization or validation before the ingested data is processed by the agent.
Audit Metadata