formal-spec
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is focused on system design analysis and TLA+ code generation. It does not perform high-risk actions such as network communication or credential harvesting.
- [SAFE]: The skill explicitly defines its scope to exclude the execution of model checkers or the modification of implementation code, adhering to a principle of least privilege.
- [SAFE]: No obfuscation techniques, prompt injection patterns, or persistence mechanisms were detected in the instructions or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect injection as it processes external system designs and protocol descriptions (ingestion points in SKILL.md). However, it lacks exploitable capabilities beyond text generation and explicitly states that no user-provided values are used in commands or file paths (sanitization). No boundary markers are specified for the inputs, but the risk is assessed as safe due to the restricted output format (TLA+ code).
Audit Metadata