flatten-pr-graph
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub Pull Requests, which could contain malicious instructions intended to influence the agent's behavior during conflict resolution or branch management.
- Ingestion points: Processes PR descriptions, commit messages, and Git history as specified in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within PR data are present.
- Capability inventory: The skill allows the agent to update branches and resolve merge conflicts (file system writes).
- Sanitization: There are no instructions for sanitizing or validating the content retrieved from PRs before it is used to inform git operations.
Audit Metadata