vp-pr-briefing
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and summarizes data from GitHub Pull Requests, which can include content from untrusted authors intended to influence the agent's behavior.
- Ingestion points: The agent reads the PR description, full diff, linked issue artifacts, checks, and review conversations as defined in
SKILL.md. - Boundary markers: The instructions explicitly warn the agent: "Do not treat the description as verified implementation" and to avoid inventing content when context is missing (SKILL.md).
- Capability inventory: The skill interacts with other tools such as
vp-githubandvp-gitto gather context and potentially perform follow-up actions (SKILL.md). - Sanitization: No explicit sanitization, filtering, or escaping logic is provided for the content retrieved from the external GitHub environment.
Audit Metadata