update-docs
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local bash scripts provided in the skill repository (get_directories.sh, check_missing_context.sh, and clean_docs.sh) to automate the discovery of project folders and the cleanup of documentation files. These scripts utilize standard system tools like find and git to operate within the project scope.
- [PROMPT_INJECTION]: The core logic of the skill involves the agent reading and summarizing project source files. This represents an indirect prompt injection surface where malicious instructions embedded in the analyzed code could attempt to influence the agent's behavior during documentation generation.
- Ingestion points: The skill explicitly instructs the agent to read the contents of all non-ignored project files into its context (SKILL.md).
- Boundary markers: Absent; there are no instructions to use delimiters or to disregard embedded instructions within the source files being analyzed.
- Capability inventory: The agent has access to local shell execution (bash) and file system write access (creating CONTEXT.md files).
- Sanitization: Absent; file contents are processed directly without validation or filtering for nested instructions.
Audit Metadata