one-off-operations
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources such as spreadsheets, database nodes, files, or user-pasted content.
- Ingestion points: External data sources identified in
SKILL.md(spreadsheets, files, tables, sheets). - Boundary markers: No specific boundary markers or "ignore embedded instructions" warnings are defined for the data ingestion phase.
- Capability inventory: The skill utilizes
build-workflow,workflows, andexecutionstools, which have the capability to write to external systems and execute complex logic. - Sanitization: The risk is mitigated by explicit instructions to use a "run-approval card" as a consent gate and requirements to read back actual node outputs to verify data integrity before reporting success to the user.
Audit Metadata