social-audit
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process untrusted data pasted by users (e.g., social media posts and bios), which represents an indirect prompt injection surface. However, the risk is negligible as the skill lacks capabilities to perform dangerous operations like network requests or system file modifications.
- Ingestion points: User-pasted social media content and profile metadata as described in the 'Workflow' section of
SKILL.md. - Boundary markers: Absent. The instructions do not mandate the use of specific delimiters to separate user data from the agent's core instructions.
- Capability inventory: The skill is restricted to text analysis, scoring, and content generation. It does not utilize any tools for network access or shell execution.
- Sanitization: No explicit sanitization or filtering of the user-provided text is defined in the instructions.
Audit Metadata