codeguard-yaml
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses the legitimate and well-known 'yamllint' tool for project diagnostics. It explicitly mandates that tools should not be silently installed or dependencies upgraded, ensuring the user maintains control over the local environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes YAML files which serve as a potential entry point for untrusted content.
- Ingestion points: Repository files with '.yml' and '.yaml' extensions (SKILL.md).
- Boundary markers: Absent; the skill does not define specific delimiters to separate file content from the agent's internal instructions.
- Capability inventory: Execution of local CLI tools ('yamllint') and modification of local files during formatting or fixing phases.
- Sanitization: Absent; the skill relies on the external linter's parser to interpret and validate the content.
Audit Metadata