sn-search-social-media

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill interacts exclusively with well-known and trusted external services, including GitHub, Stack Exchange, Wikimedia, and Google Firebase (Hacker News API).
  • [SAFE]: Robust content filtering is implemented in scripts/_filters.py and applied across search scripts to ensure compliance with policy restrictions on cryptocurrency-related queries.
  • [SAFE]: Credential management instructions in SKILL.md follow security best practices by recommending the use of .env files and environment variables, avoiding hardcoded secrets.
  • [SAFE]: Evaluation of indirect prompt injection surface reveals low risk:
    • Ingestion points: Data from external community APIs is ingested in scripts/github_public_search.py, scripts/hackernews_hotspots.py, scripts/stackexchange_search.py, and scripts/wikimedia_pageviews.py.
    • Boundary markers: The skill outputs results in a structured JSON format, providing clear delimitation for the agent.
    • Capability inventory: Tool capabilities are restricted to network read operations (GET requests) and JSON formatting; no dangerous execution sinks (eval, exec) or filesystem write operations are present.
    • Sanitization: Scripts implement HTML stripping and unescaping (e.g., in scripts/stackexchange_search.py and scripts/hackernews_hotspots.py) to sanitize data before ingestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 10:41 AM
Security Audit — agent-trust-hub — sn-search-social-media