commit-message-formatter
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and metadata. No malicious code, obfuscation, or persistence mechanisms were detected.
- [NO_CODE]: This skill does not include any scripts, binaries, or implementation code. Its functionality relies on standard agent capabilities guided by instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied data (commit messages) while having access to sensitive tools, creating a theoretical attack surface.
- Ingestion points: User requests containing commit message patterns, best practices, or specific "commit" phrases (SKILL.md).
- Boundary markers: None specified; instructions do not explicitly tell the agent to ignore instructions embedded in formatted text.
- Capability inventory: The skill is configured with broad tool access, including unrestricted bash command execution and file modification (SKILL.md).
- Sanitization: No specific input validation or sanitization procedures are defined in the instructions.
Audit Metadata