pattern-of-life-from-socials

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of instructional documentation and checklists for performing social media OSINT. No executable scripts, network operations, or sensitive data access patterns were detected.\n- [SAFE]: All referenced external URLs belong to the vendor's domain (useosint.com), representing legitimate documentation and support resources for the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting and analyzing untrusted data from social media platforms.\n
  • Ingestion points: Social media profile metadata, posts, and media content as defined in the analytic checklist.\n
  • Boundary markers: The workflow mandates an authorized scope and verification of manual activity, though it lacks programmatic prompt delimiters.\n
  • Capability inventory: References specialized tools for metadata extraction, geolocation, and network analysis.\n
  • Sanitization: Relies on manual cross-referencing and an evidence-based grading system to mitigate risks from untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:47 PM
Security Audit — agent-trust-hub — pattern-of-life-from-socials