Skills
skills/allinherog-star/ai-skills/ai-customer-pulse/Gen Agent Trust Hub

ai-customer-pulse

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection due to its processing of untrusted external content.\n
  • Ingestion points: User-supplied data is ingested via the materialText, materialFile, and materialUrl parameters as defined in references/form-schema.json.\n
  • Boundary markers: The instructions do not specify delimiters or warnings for the agent to ignore instructions contained within the analyzed materials.\n
  • Capability inventory: The skill utilizes a Python script (scripts/run.py) to transmit ingested data to the vendor's API at ai-skills.ai.\n
  • Sanitization: No evidence of input validation, filtering, or escaping for the external content is present in the analyzed files.\n- [EXTERNAL_DOWNLOADS]: The skill performs network operations and references external information sources.\n
  • The script scripts/run.py makes network requests to the vendor's domain ai-skills.ai to execute its core functionality.\n
  • Skill metadata in references/skill.json references resources from skillsmp.com and the trusted organization repository anthropics/knowledge-work-plugins.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:30 AM
Security Audit — agent-trust-hub — ai-customer-pulse