github-action-review
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or behaviors were identified in the skill. The instructions focus on best practices for shell scripts, token handling, and robust data processing.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review untrusted external data in the form of changed code files, representing a potential indirect prompt injection surface.
- Ingestion points:
SKILL.mdinstructs the agent to review 'actual changed scripts, jq filters, action definition, and tests'. - Boundary markers: None specified in the instructions.
- Capability inventory: The skill is primarily instructional for review; it does not explicitly invoke shell commands, network operations, or file-write capabilities within the provided scope.
- Sanitization: No sanitization or filtering logic for the ingested code content is described.
Audit Metadata