recipe-front-review
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as
ls,grep, andgit diffto locate design documents and identify modified source files for evaluation. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and analyzes untrusted data from external files (Design Docs and implementation source code) to perform its core functions. 1. Ingestion points: File contents identified via
docs/design/*.mdandgit diff. 2. Boundary markers: The skill does not employ specific delimiters or instructions to ignore commands embedded within the processed text. 3. Capability inventory: The skill has the ability to read project files, write new task plans to the file system, and perform automated code modifications through sub-agents. 4. Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the analyzed files before it is processed by the AI agents.
Audit Metadata