pr-review
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to ingest and analyze untrusted data from external Pull Request URLs.
- Ingestion points: SKILL.md (Workflow step 2
- Analyzing code and tests from the provided PR URL).
- Boundary markers: Absent. The skill does not provide delimiters or instructions to ignore embedded commands within the PR content.
- Capability inventory: SKILL.md (Workflow steps 1 and 3
- Git operations including adding remotes and checking conflicts).
- Sanitization: Absent. There are no instructions to sanitize or validate the content retrieved from the PR.
Audit Metadata