social-media-expert
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains legitimate educational content, best practices, and boilerplate code for building social media applications. No evidence of malicious intent, credential exfiltration, or obfuscation was detected.
- [INDIRECT_PROMPT_INJECTION]: The code templates demonstrate the processing of untrusted external data (such as social media comments), which represents an attack surface for indirect prompt injection.
- Ingestion points: The
SocialMediaManager.track_commentmethod inreferences/EXAMPLES.mdaccepts and processes raw text from comments. - Boundary markers: No delimiters or specific instructions for the agent to ignore embedded commands are present in the provided templates.
- Capability inventory: The skill has access to
Read,Write, andWebSearchtools. - Sanitization: No input sanitization or safety filtering is implemented in the template logic.
Audit Metadata