app-intents-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of informational Markdown files designed to guide an AI agent through a code review process. No active code (Python, JavaScript, or Shell) is included in the skill package.
- [SAFE]: No instances of prompt injection, obfuscation, or persistence mechanisms were found. Instructions reinforce development best practices such as thread safety and performance constraints.
- [SAFE]: All external references are internal relative links to local documentation within the skill structure.
- [INDIRECT_PROMPT_INJECTION]: The skill reviews user-provided code, which serves as an ingestion point for untrusted data. However, since the skill has no executable capabilities or tools to perform automated actions, the risk is categorized as safe. Boundary markers and sanitization are absent, but the lack of exploitable capabilities (no scripts, tools, or write operations) effectively mitigates the threat.
Audit Metadata