event-content-repurposing
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data sources, which constitutes a vulnerability surface for indirect prompt injection.\n
- Ingestion points: The skill ingests transcripts, hallway notes, slides, and photo archives as primary inputs for content repurposing.\n
- Boundary markers: The instructions do not define specific delimiters or isolation techniques to separate untrusted external content from the agent's command context.\n
- Capability inventory: The skill is primarily instructional and does not include scripts or request specific tool permissions in its YAML frontmatter; however, the agent's default environment may have tool-access capabilities.\n
- Sanitization: No input validation, sanitization, or escaping of the external data is specified in the workflow.
Audit Metadata