scenario-quality-gate
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest feedback (specifically 'reasons' and 'suggestions') from the 'asset_quality_gate_run' tool and incorporate it into the next iteration's prompt.
- Ingestion points: Feedback from 'asset_quality_gate_run' tool output in SKILL.md.
- Boundary markers: None identified; the instructions suggest direct translation of suggestions into subsequent prompts.
- Capability inventory: Uses 'scenario_tool_execute_write' to perform 'model_run' and 'asset_quality_gate_run' actions.
- Sanitization: No sanitization, filtering, or escaping of the tool's output is mentioned before its use in prompt interpolation.
- [COMMAND_EXECUTION]: The skill documentation includes the command 'npx skills add scenario-labs/skills --skill ' to install sibling skills.
- Evidence: The command targets the official repository of the authoring vendor ('scenario-labs') and is part of the standard platform workflow.
Audit Metadata