workshop-builder
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and process external data including project files, run notes, audience details, and hardware inventory. This creates a surface for instructions embedded in those external files to influence the agent's behavior. \n
- Ingestion points: SKILL.md specifies reading project context, run notes, and audience information. \n
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat this external content as untrusted or to ignore instructions found within it. \n
- Capability inventory: The skill focuses on generating a workshop plan, exercise cards, and checklists. It does not explicitly call for file system writes, network requests, or code execution, though it operates within the agent's default environment. \n
- Sanitization: No input validation or sanitization steps are defined for the ingested context.
Audit Metadata