audit-gate-logic
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external sources, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in the code or configuration being audited.
- Ingestion points: The skill reads content from
.github/workflows/*, repository settings viagh api, and various baseline/configuration files like.eslintignoreandcoveragePathIgnorePatterns(SKILL.md). - Boundary markers: The instructions lack specific requirements for using delimiters or boundary markers when the agent interpolates the content of these external files into its context.
- Capability inventory: The skill has the capability to read files and query repository metadata via the
gh apitool. It is explicitly restricted to read-only operations and is instructed not to modify workflows or branch protection rules. - Sanitization: There are no instructions for the agent to sanitize, escape, or validate the content retrieved from external files before it is processed or used to generate findings.
Audit Metadata