space-mermaid-diagram
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing untrusted user input and writing it to the local filesystem. Ingestion points: Arbitrary user text, workflows, and logic descriptions defined in SKILL.md. Boundary markers: Absent; instructions do not include delimiters or warnings to ignore embedded instructions. Capability inventory: File system writes to local directories as specified in the storage instructions in SKILL.md. Sanitization: Absent; no input validation or filtering is specified.
Audit Metadata