wiki-page-writer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
git remote get-url originandgit rev-parse --abbrev-ref HEADto resolve the repository context. This is used to construct valid link citations for the generated documentation.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is instructed to "Read all relevant files" to analyze code paths and patterns. - Ingestion points: Local source code files in the user's repository (file analysis step).
- Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between file content and instructions.
- Capability inventory: The skill's capabilities are limited to reading files, querying git metadata, and outputting markdown text.
- Sanitization: No sanitization is performed on the ingested code content before the agent processes it for documentation generation.
Audit Metadata