devdocs-retrofit

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Bash commands to scan project directory structures and perform file renames using git mv to maintain version control history during documentation migration.
  • [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection because it analyzes untrusted project content (such as code, API endpoints, and test descriptions) to derive documentation structure. 1. Ingestion points: SKILL.md (Step 4: Code Reverse Engineering) describes analyzing routes and test files to infer requirements. 2. Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands mentioned when processing extracted code data. 3. Capability inventory: The agent possesses Bash and Write capabilities for file management and documentation creation. 4. Sanitization: No specific sanitization or filtering logic is described for the content extracted from project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 06:08 AM