Skills
skills/allinherog-star/ai-skills/email-sequence/Gen Agent Trust Hub

email-sequence

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from external sources, presenting an indirect prompt injection surface.
  • Ingestion points: Untrusted data enters the agent context via materialUrl, materialFile, and materialText as specified in references/form-schema.json.
  • Boundary markers: The skill does not implement delimiters or explicit instructions to the agent to disregard commands embedded within the input data.
  • Capability inventory: The skill employs scripts/run.py to perform network requests and data transmission to the vendor API at ai-skills.ai.
  • Sanitization: No validation or sanitization of input data is performed in the provided scripts before processing.
  • [EXTERNAL_DOWNLOADS]: The Python runner script (scripts/run.py) performs network requests to ai-skills.ai to communicate with the backend service. This domain is the primary infrastructure for the skill author.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:31 AM
Security Audit — agent-trust-hub — email-sequence