integrate-context-matic

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of third-party SDKs and packages (e.g., via npm install, pip install) based on information retrieved from the context-matic MCP server. These dependencies are not verified against a trusted source within the skill's instructions.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through ingestion of data from the context-matic MCP server via the fetch_api and ask tools. * Ingestion points: fetch_api, ask, model_search, endpoint_search (SKILL.md). * Boundary markers: Absent; no instructions provided to treat external guidance as untrusted. * Capability inventory: Package installation commands (npm, pip, go), workspace modifications (add_guidelines, add_skills). * Sanitization: Absent.
  • [DATA_EXFILTRATION]: The skill references sensitive file paths, specifically .env files and secrets managers, to verify the auth_configured milestone during API integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 01:04 AM