social-crisis-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists exclusively of Markdown documentation describing workflows and best practices. There are no executable scripts (.py, .js, .sh), binary files, or configuration files provided.
  • [EXTERNAL_DOWNLOADS] (SAFE): No external dependencies are referenced. There are no calls to package managers like pip or npm, and no remote code execution patterns using curl or wget.
  • [PROMPT_INJECTION] (SAFE): The instructions are purely instructional and do not contain adversarial patterns aimed at overriding the agent's safety filters or extracting its system prompt.
  • [DATA_EXFILTRATION] (SAFE): There are no network operations, hardcoded credentials, or attempts to access sensitive system files.
  • [INDIRECT_PROMPT_INJECTION] (LOW): While the skill describes workflows for monitoring social media mentions (data ingestion), it does not provide any implementation code or tool definitions that would introduce a specific vulnerability surface. The risk is inherent to the general task of processing untrusted content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:41 PM