triage-prs
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to read and interpret data from pull request titles, bodies, and linked issues to automate labeling and commenting. Because this data originates from external contributors, it represents a potential surface where an author might attempt to influence the agent's triage decisions through carefully crafted content.
- Ingestion points: Data is ingested from pull request titles, bodies, file paths, and metadata from linked issues in
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' markers to separate untrusted pull request content from the agent's core instructions.
- Capability inventory: The skill utilizes GitHub capabilities to apply/remove labels, post comments, and modify the draft status of pull requests.
- Sanitization: The logic relies on pattern matching (such as Conventional Commit prefixes) but does not explicitly define sanitization or validation steps for the incoming data strings.
Audit Metadata