pavlo-pr-writer
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data from tickets and git history to generate pull request summaries.
- Ingestion points: Ticket descriptions, acceptance criteria, plan documents, and rewritten commit messages referenced in SKILL.md.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to separate instructions from untrusted external content.
- Capability inventory: The skill utilizes the
show_contenttool to display output to the user; it lacks capabilities for network access, system command execution, or persistent file modification. - Sanitization: No explicit sanitization, filtering, or escaping of the ingested external content is performed.
Audit Metadata