py-type-safety
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review user-provided Python code, creating a surface for indirect prompt injection.\n
- Ingestion points: The skill analyzes Python source code provided by the user in the agent context as described in the review rules in SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters or explicit 'ignore embedded instructions' warnings for the content being reviewed.\n
- Capability inventory: The skill does not define or use any dangerous capabilities such as file system writes, network requests, or shell command execution across any scripts.\n
- Sanitization: No sanitization, escaping, or validation logic is provided for the input code content.\n- [SAFE]: The skill includes a 'Sensitive Evidence Safety' section that provides defensive guidelines to the agent, instructing it not to reproduce or quote detected credentials or secrets found during code reviews.\n- [SAFE]: References to external documentation (docs.python.org) target a well-known, trusted official service and do not involve remote code execution or data exfiltration.
Audit Metadata