create-doc
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
ls docs/to retrieve a list of existing documentation categories. This allows the agent to correctly classify new documentation files within the project structure. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted data from the conversation history to generate persistent files. Ingestion points: The agent reads previous messages to identify conventions, benefits, and examples (Step 1). Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between the user's intent and potentially malicious content within the analyzed text. Capability inventory: The skill can list directories, read guideline files, and write/update files in the
docs/directory andAGENTS.md. Sanitization: The instructions do not define any validation or escaping mechanisms for the content being extracted. - [SAFE]: The external link provided in the skill redirects to
codely.com, which is the official domain of the author (Codely), representing standard and safe functionality for this skill.
Audit Metadata