feature-spec
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of markdown text instructions. It does not contain any executable code, scripts, or external dependencies.
- [PROMPT_INJECTION] (SAFE): No instructions to bypass safety filters or override system prompts were identified.
- [DATA_EXFILTRATION] (SAFE): The skill does not perform any network requests or access sensitive local directories.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes user-provided feature descriptions. Evidence: 1. Ingestion points: User input provided to the prompt; 2. Boundary markers: Absent; 3. Capability inventory: None (no shell, network, or file access); 4. Sanitization: Absent. Since the skill has no tool-calling capabilities, the risk of exploitation is negligible.
Audit Metadata