breadcrumbs-testing-guide
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill implements documentation validation through standard shell commands including
rg,find,grep,sed,sort,comm, andls. These tools are used appropriately for searching patterns and verifying file existence without modifying the documentation files. - [PROMPT_INJECTION]: The skill was analyzed for indirect prompt injection risks as it processes user-provided markdown documentation.
- Ingestion points: Markdown files within the local vault (file: SKILL.md).
- Boundary markers: None present in the provided instructions.
- Capability inventory: Access to shell command execution for read-only pattern matching and file metadata comparison (file: SKILL.md).
- Sanitization: Content is not sanitized before being processed by the shell utilities, but the risk is mitigated by the non-evaluative nature of the search commands.
Audit Metadata