content-pillar-builder
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data provided via the '[WHAT]', '[WHO]', and '[paste if available]' (Recent posts) placeholders in
SKILL.md. - Boundary markers: Absent. The prompt template interpolates user input directly into the strategist instructions without delimiters or 'ignore' directives.
- Capability inventory: No specific tool invocations or dangerous capabilities (like file writing or network access) are defined within the skill's instructions.
- Sanitization: Absent. There is no evidence of filtering, validation, or escaping of the user-provided strings before they are processed by the model.
Audit Metadata