gha-audit
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze GitHub Actions workflow files from the repository (
.github/workflows/). This creates an attack surface where untrusted data (the workflow content) is processed by the agent to generate output (a report and a diff). Malicious instructions hidden in comments or strings within a workflow could attempt to trick the agent into recommending harmful changes or reporting false results. - Ingestion points: Workflow files in
.github/workflows/and files provided via the$ARGUMENTSvariable. - Boundary markers: Absent; there are no specific delimiters or instructions provided to the model to ignore potential commands embedded within the data it is auditing.
- Capability inventory: The skill reads file contents and generates code diffs and text reports. It does not perform network operations or direct file modifications without user oversight.
- Sanitization: No evidence of sanitization or validation of the ingested file content before it is passed to the audit tool.
Audit Metadata