github-actions-author
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it is designed to ingest and analyze untrusted content from the local workspace.
- Ingestion points: The workflow involves reading existing workflow files,
package.json, lockfiles, workspace configurations, and test scripts (SKILL.md). - Boundary markers: The instructions do not specify any delimiters or explicit 'ignore' instructions for the agent when processing these external files.
- Capability inventory: The skill uses the GitHub CLI (
gh) andgitto query repository metadata and has the capability to write or modify YAML files in the.github/workflows/directory. - Sanitization: There is no evidence of programmatic sanitization or validation of the content ingested from the repository before it is evaluated by the agent.
Audit Metadata