discovery-workshop
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its document synthesis workflow.
- Ingestion points: Untrusted workshop notes are ingested via user input and the
Readtool as defined inSKILL.md. - Boundary markers: The prompt does not include delimiters or instructions to the model to ignore commands embedded in user-provided notes.
- Capability inventory: The skill is granted
Write,Edit,Grep, andGlobtools, which provide a path for potential unauthorized file system changes if a malicious prompt is processed. - Sanitization: No input validation or content filtering is implemented for the processed workshop notes.
Audit Metadata