github-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interacts with untrusted data from GitHub pull requests and issues.
- Ingestion points: The agent retrieves external content using commands like
gh pr view,gh pr diff, andgh issue viewin SKILL.md. - Boundary markers: The skill does not provide delimiters or specific instructions to the agent to treat fetched content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill enables the agent to perform state-changing operations such as
gh pr merge,gh pr review --approve, andgh issue close. - Sanitization: No sanitization or validation logic is defined for the content retrieved from GitHub.
- [NO_CODE]: This skill consists entirely of markdown instructions and does not include any executable scripts, binaries, or configuration files that run code.
Audit Metadata