harmonize-docs
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the repository to perform its core functions.
- Ingestion points: The workflow requires reading all human-authored documentation, plans, source code, configuration files, and test files to "reconstruct truth" and verify claims (SKILL.md, Step 2).
- Boundary markers: The instructions do not specify any delimiters or explicit warnings to the agent to disregard instructions embedded within the processed documentation files.
- Capability inventory: The agent has the authority to read, write, create, move, and delete files throughout the repository (SKILL.md, Step 4), and can coordinate work through subagents.
- Sanitization: The skill does not describe any sanitization, filtering, or escaping of the content read from the repository before it is integrated into the final harmonious rewrite.
Audit Metadata