create-pull-request
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection as it ingests untrusted data from project files, commit messages, and git diffs to generate PR descriptions.
- Ingestion points: Reads git diffs, commit messages, and existing project PR templates.
- Boundary markers: The instructions do not explicitly require the agent to use XML tags or specific delimiters when processing these inputs to separate data from instructions.
- Capability inventory: The skill has the capability to read files, capture visual evidence (screenshots), and publish content to a PR host (via tool calls).
- Sanitization: The skill includes instructions to omit session IDs and internal execution metadata from the generated output, providing a basic level of output filtering.
Audit Metadata