github-actions-pro
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [EXTERNAL_DOWNLOADS] (INFO): References standard, high-trust GitHub Actions including
actions/checkout,aws-actions/configure-aws-credentials, andoven-sh/setup-bun. These are from trusted organizations and the skill explicitly recommends pinning to commit SHAs for maximum security. - [DATA_EXFILTRATION] (SAFE): The skill actively discourages the use of long-lived secrets like
AWS_ACCESS_KEY_IDin favor of OIDC, reducing the risk of credential exposure. - [INDIRECT_PROMPT_INJECTION] (LOW): The skill's primary function involves reading and auditing external workflow files. While this is an ingestion point for untrusted data, the capability is used for security analysis rather than executing untrusted commands.
- [PROMPT_INJECTION] (SAFE): No attempts to override agent constraints or bypass safety filters were found in the instructional text.
Audit Metadata