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