action-item-organizer
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted text sources such as reports, meeting notes, and audit findings, which presents a surface for indirect prompt injection.
- Ingestion points: The
Extraction WorkflowinSKILL.mdinstructs the agent to read and analyze complete source documents, including prose and lists. - Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions that might be embedded within the source documents being processed.
- Capability inventory: The skill is purely instructional markdown and does not request access to any sensitive tools, network operations, or file system modifications beyond the generated markdown output.
- Sanitization: There are no instructions for sanitizing or escaping the content extracted from source documents before it is interpolated into the final markdown checklist.
Audit Metadata