emergency-distress-signal
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The analyzed files consist entirely of narrative text and metadata. No scripts, binaries, or automated tasks were found.- [NO_CODE]: The skill provides story beats and dialogue examples in Markdown format without any functional code dependencies (Python, Node.js, etc.).- [PROMPT_INJECTION]: The character roleplay instructions are purely for storytelling purposes and do not attempt to bypass AI safety protocols or extract system prompts.- [INDIRECT_PROMPT_INJECTION]: The skill establishes a safe conversational surface. While it processes user input for narrative branching, it does not possess any risky capabilities (such as file system access or network operations) that could be exploited. 1. Ingestion points: Interactive dialogue flows in SKILL.md. 2. Boundary markers: Scenario examples are delimited by markdown formatting. 3. Capability inventory: No dangerous tools or subprocess calls are present. 4. Sanitization: N/A.
Audit Metadata