skills/simota/agent-skills/helm/Gen Agent Trust Hub

helm

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily composed of strategic instructions and knowledge references. It expressly prohibits code generation and executive decision-making, significantly reducing the potential for automated abuse.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a common vulnerability surface where untrusted data could influence agent behavior.
  • Ingestion points: Market data collected via the WebSearch tool and inputs from external agents such as Compete, Pulse, and Researcher as defined in the 'COLLABORATION_PATTERNS' section of SKILL.md.
  • Boundary markers: The instructions lack specific delimiters or instructions to ignore potential commands embedded within external data sources.
  • Capability inventory: Access to WebSearch and the ability to generate execution roadmaps that are handed off to other agents (e.g., Sherpa).
  • Sanitization: No explicit sanitization, filtering, or validation processes are described for content retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 12:03 PM