opportunity-map

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes potentially untrusted discovery data (e.g., JTBD analysis, Lean Canvas, research findings) to generate prioritization maps, which is a known vector for indirect prompt injection attacks.
  • Ingestion points: As described in the 'Prerequisites' section of SKILL.md, the skill reads 'discovery-output' and other research artifacts from the conversation or project files.
  • Boundary markers: The instructions lack requirements for delimiters or explicit 'ignore embedded instructions' markers when processing the ingested data.
  • Capability inventory: The skill is authorized to write markdown documents to .jimmy/docs/opportunity-map.md and .jimmy/decisions.md, but it has no capabilities for network communication or code execution.
  • Sanitization: No sanitization, validation, or filtering of the external research data is performed prior to its interpolation into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:13 PM
Security Audit — agent-trust-hub — opportunity-map