social-audit
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for text analysis of user-provided data. It does not use external tools, execute code, or perform network operations. The file access is restricted to the skill's own configuration files (social-context.md or .agents/social-context.md).- [PROMPT_INJECTION]: The skill processes untrusted user-pasted data, such as social media posts and profile bios. This creates a surface for indirect prompt injection where instructions hidden in the pasted content could attempt to influence the audit results. However, this is assessed as safe because the skill has no access to dangerous tools like shell execution or network requests.
- Ingestion points: Recent posts and bio text pasted by the user into the chat (SKILL.md workflow).
- Boundary markers: No specific delimiters or boundary markers are defined to isolate user content from the skill's instructions.
- Capability inventory: The skill utilizes no external tools, network calls, or filesystem write operations.
- Sanitization: No sanitization or filtering is applied to the user-pasted content before analysis.
Audit Metadata