ai-output-verifier
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external text (AI-generated responses provided by the user). While this constitutes an untrusted data ingestion point, the skill lacks any actionable capabilities, tools, or shell access that could be misused if a malicious prompt were embedded in the analyzed text.
- Ingestion points: User-pasted AI output as defined in the 'Required Inputs' section of SKILL.md.
- Boundary markers: The skill does not explicitly define delimiters for the input text.
- Capability inventory: None. The skill is limited to generating text-based analysis and does not invoke any tools.
- Sanitization: No specific sanitization or filtering logic is defined for the input content.
Audit Metadata