kiro-verify-completion
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on defining a systematic verification process for tasks, fixes, and builds. No executable scripts, binaries, network requests, or credential harvesting patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting and processing untrusted data from command outputs and task metadata, which is standard for verification workflows. While the skill lacks explicit boundary markers or sanitization rules, it mitigates risk by requiring specific empirical evidence like exit codes and failure counts.
- Ingestion points: 'Validation commands' and 'Fresh command output' inputs defined in SKILL.md.
- Boundary markers: None specified.
- Capability inventory: The agent evaluates command outputs typically generated through shell execution.
- Sanitization: No explicit sanitization or escaping of input data is mentioned.
Audit Metadata