documentation-writer
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to test commands for accuracy using the bash tool. This creates a risk where the agent might execute malicious commands if they are present in the documentation or project scripts being analyzed.
- [PROMPT_INJECTION]: The skill operates on local project files which serves as an indirect prompt injection surface.
- Ingestion points: Files in
source/,docs/,scripts/, and.claude/commands/are read for analysis. - Boundary markers: Absent; the skill does not define clear separators or warnings for instructions embedded in data.
- Capability inventory: The agent has access to file system tools (Read, Write, Edit, Grep, Glob) and shell execution (Bash).
- Sanitization: Absent; no content validation or filtering is performed on project files before analysis.
Audit Metadata