grill-my-idea
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or high-risk behaviors were detected. The skill's logic is transparent and focuses on structured analysis of user-provided ideas.
- [COMMAND_EXECUTION]: The skill instructs the agent to create directories and write markdown files (e.g., docs/ai-native/01-grill-my-idea.md). These are standard file system operations intended for documentation and do not involve executing untrusted shell commands or scripts.
- [PROMPT_INJECTION]: The skill ingests untrusted user input in the form of raw app ideas. While it represents an attack surface for indirect prompt injection, the risk is negligible as the output is static markdown and is not processed by any executable tools. (1) Ingestion points: User-provided app ideas via the 'Inputs' section. (2) Boundary markers: No specific delimiters or ignore instructions are defined. (3) Capability inventory: File system write access to the project's documentation directory. (4) Sanitization: No explicit validation or filtering of user content is mentioned.
Audit Metadata