profile-optimization

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to the ingestion of untrusted local data without isolation.
  • Ingestion points: The skill's instructions in SKILL.md (Step 0) require the agent to load and read content from brand-profile.md, social-strategy.md, audience.md, and voice.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore any embedded commands or formatting within the ingested files.
  • Capability inventory: The agent has the capability to generate text across multiple platform specifications and can trigger other skills, including image generation via ideogram.md and nano-banana.md.
  • Sanitization: No validation or filtering is applied to the content of the ingested files before they are incorporated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 02:27 PM
Security Audit — agent-trust-hub — profile-optimization