ideal-customer-profile

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted research data (survey responses, interview transcripts, and support tickets) that could contain malicious instructions designed to manipulate the agent's reasoning or poison the core 'brain' context.
  • Ingestion points: The skill intake in Step 1 and the Inputs section of SKILL.md explicitly accept external research data for synthesis.
  • Boundary markers: There are no specific delimiters defined for the ingested research data, though the skill requires explicit user confirmation before writing the final synthesized profile to /foundation/brain.md.
  • Capability inventory: The skill has read access to /foundation/brain.md and /context/meta-patterns.md, and it has write access (append-only) to /foundation/brain.md and /context/skill-sessions.md.
  • Sanitization: No sanitization, filtering, or escaping mechanisms are specified for handling instructions that might be embedded within the research data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 06:36 AM
Security Audit — agent-trust-hub — ideal-customer-profile