github-delivery
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which could be exploited for indirect prompt injection.
- Ingestion points: The workflow requires the agent to inspect 'repository instructions', 'review feedback' from GitHub, and 'CI failing job/log' output as described in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potential commands embedded within code reviews or log files.
- Capability inventory: The skill assumes the ability to execute git and GitHub CLI commands, including committing code and creating pull requests.
- Sanitization: No sanitization or filtering logic is defined for the external inputs handled during the delivery process.
Audit Metadata