collab-status-report
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided KPI metrics and existing report files. This represents an attack surface where malicious instructions could be embedded in the data provided to the agent.
- Ingestion points: The workflow specifies collecting KPI data from user input or existing files in step 2.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands within the ingested data.
- Capability inventory: The skill performs data aggregation, markdown table formatting, and routes content to other skills (
moai-coworker,moai-writer,moai-officer,moai-analyst) for post-processing. - Sanitization: No specific filtering or sanitization logic is described for the input data.
Audit Metadata