social-graph-ranker

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists of documentation and mathematical formulas for a social graph ranking engine. No executable code is provided within the file.
  • [NO_CODE]: The skill is entirely descriptive and does not include scripts, executables, or package dependencies.
  • [PROMPT_INJECTION]: The skill defines a workflow for processing untrusted external data from X and LinkedIn. While this represents a surface for indirect prompt injection, no specific vulnerabilities or malicious instructions are present. Ingestion points: User graph data and target lists from X/LinkedIn. Boundary markers: None specified. Capability inventory: Uses x-api for data access. Sanitization: No data validation or cleaning steps are described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:20 AM
Security Audit — agent-trust-hub — social-graph-ranker