yy-anti-distill
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
- Ingestion points: The skill reads external files such as work.md, persona.md, and other user-provided Markdown, PDF, or TXT documents for processing as defined in Step 1.
- Boundary markers: The instructions do not establish delimiters or provide warnings to the agent to ignore instructions embedded within the processed data.
- Capability inventory: The agent is directed to use recursive glob searching (**/SKILL.md) and file read/write operations across the file system.
- Sanitization: No sanitization or content validation is performed on the input data before the agent classifies it. Although Step 4 includes a user confirmation checkpoint, the analysis and classification steps remain vulnerable to directives hidden in the ingested documents.
Audit Metadata