parity-gap
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill maps and diffs content from external reference sources such as remote repositories or specification files, creating an ingestion point for untrusted instructions.
- Ingestion points: Remote repositories (cloned), local paths, and documentation files provided as the 'reference' (SKILL.md, Section 1).
- Boundary markers: No specific delimiters or instructions are provided to ignore embedded commands within the reference material.
- Capability inventory: The skill uses tools for cloning repositories, searching code (Grep/Read), and writing to the local file system (docs/todo.md).
- Sanitization: There are no sanitization or validation protocols for the ingested content.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the cloning of remote repositories into a temporary directory to perform analysis (SKILL.md, Section 1).
Audit Metadata