social-media-osint
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions for an OSINT workflow. It does not contain executable scripts, hardcoded credentials, or unauthorized network operations. It appropriately references an ethics policy and limits its scope to public data.
- [PROMPT_INJECTION]: The skill instructions involve processing untrusted data from social media profiles, which represents an attack surface for indirect prompt injection.
- Ingestion points: Social media handles, profile bios, post text, and media content (SKILL.md).
- Boundary markers: None explicitly defined for external content.
- Capability inventory: Includes tools for image metadata analysis, archive retrieval, and reporting (SKILL.md).
- Sanitization: No specific sanitization or data validation steps are prescribed for the ingested content.
Audit Metadata