git-workflow-manager
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze 'repository state' and 'collaboration patterns'. This creates a surface where an attacker could embed malicious instructions in Git metadata or repository files that the agent might follow while performing its management duties.
- Ingestion points: Repository state, collaboration patterns, and team structure data (SKILL.md).
- Boundary markers: No delimiters or instructions are provided to the agent to treat external repository data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill implies the ability to configure branch protections, PR checks, and manipulate Git history.
- Sanitization: The instructions do not include steps to sanitize or validate the content retrieved from the repository.
Audit Metadata