github-actions-hardening
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a comprehensive security auditing framework for GitHub Actions workflows. It correctly identifies and mitigates critical threat vectors including script injection via expression interpolation, privilege escalation through triggers like
pull_request_target, and supply chain risks associated with mutable action references.\n- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted GitHub Actions workflow files, creating an indirect injection surface. Although the risk is low for a reasoning-focused auditing tool, the following factors are noted:\n - Ingestion points: Untrusted data enters the agent context through GitHub Actions workflow files (
.github/workflows/*.yml) as described inSKILL.md.\n - Boundary markers: The instructions do not explicitly mandate the use of delimiters or 'ignore' instructions when reading untrusted workflow files.\n
- Capability inventory: The skill performs complex reasoning and reporting tasks; it does not explicitly use dangerous tool capabilities like network access or file-writing in its defined workflow.\n
- Sanitization: No explicit sanitization or filtering of the ingested workflow content is described in the skill's instructions.
Audit Metadata