harmonize-docs
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository, including human-authored documentation and source code, which it uses to verify claims and perform documentation rewrites. Maliciously crafted content within these files could attempt to influence the agent's output during the harmonization process.
- Ingestion points:
SKILL.md(Step 1 and 2) specifies reading all human-authored documentation, source code, configuration files, and repository state. - Boundary markers: There are no explicit instructions to the agent to ignore or delimit embedded instructions within the processed files.
- Capability inventory: The skill is authorized to perform file-write operations to documentation-specific files, navigation, and configuration files as described in
SKILL.md(Step 1 and 4). - Sanitization: No explicit sanitization or validation of the ingested content is defined before it is used to generate the final documentation output.
Audit Metadata