bitfsae-github-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides security-positive instructions to identify and prevent the accidental commitment of credentials, secrets, and generated artifacts to repositories. It specifically directs the agent to check diffs for secrets and ensure verification evidence is accurate.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by instructing the agent to process and analyze external, untrusted data sources.
- Ingestion points: The agent is directed to evaluate git diffs, pull request templates, and verification evidence provided within the repository context (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the external data.
- Capability inventory: The agent utilizes standard git and repository management capabilities to perform reviews and merge operations.
- Sanitization: No explicit sanitization or filtering of the processed content is specified.
- Note: This risk is considered inherent to the primary function of a repository review tool and is mitigated by the skill's explicit security instructions to prevent credential leakage.
Audit Metadata