pr-name
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from pull request titles and diffs to generate output. This creates a surface where malicious instructions embedded in a PR could attempt to influence the agent's behavior.
- Ingestion points: The agent is instructed to "inspect [the PR's] current title and diff" as the basis for its response in SKILL.md.
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions found within the diff content.
- Capability inventory: The skill focus is on text analysis and generation; it does not request file system, network, or shell execution tools.
- Sanitization: The skill does not provide mechanisms for sanitizing or escaping content retrieved from the PR diffs.
Audit Metadata