hexagon-complexity-mapper

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-provided data directly into its instructions without sanitization or boundary markers.
  • Ingestion points: Untrusted data enters the context through several input fields including topic_or_challenge, context, and existing_evidence in SKILL.md.
  • Boundary markers: There are no delimiters (e.g., XML tags, triple quotes) or specific instructions provided to the agent to differentiate between the system's instructions and the user-supplied data.
  • Capability inventory: The skill primarily generates text and does not request specific system tools, file system access, or network capabilities.
  • Sanitization: The skill does not validate, escape, or filter the content of the provided input variables before processing them in the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 11:56 AM
Security Audit — agent-trust-hub — hexagon-complexity-mapper