repo-docs
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at
<plugin root>/scripts/prose-lint.pyto validate the generated documentation. This script is part of the skill's own distribution. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository (such as README files, package manifests, and source code) and uses this information to populate documentation templates.
- Ingestion points: The agent reads the repository's README, package manifest, source layout, and design docs during the initial survey phase (SKILL.md).
- Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to ignore embedded instructions within the surveyed project files.
- Capability inventory: The skill possesses the ability to read files, write multiple documentation files to the local disk, and execute a local Python script (
prose-lint.py). - Sanitization: The workflow includes a confirmation step where the user reviews the proposed documentation scope (Step 2) and a final review of the generated layout (Step 5), which acts as a manual mitigation against malicious content injection.
Audit Metadata