hrt-align-consistency-review
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local data from multiple Markdown files which directly influences its analysis logic and automated file-editing capabilities.
- Ingestion points: discovery.md, proposal.md, specs/**/*.md, design.md, and tasks.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded agent-steering content are used when reading these files.
- Capability inventory: The skill can execute shell commands (openspec, ripgrep, codegraph) and perform automated file modifications to resolve mechanical findings.
- Sanitization: No content validation or sanitization is performed on artifact data before it is processed.
- [COMMAND_EXECUTION]: The skill invokes several command-line utilities to perform validation and codebase exploration.
- Evidence: Uses openspec validate --strict, ripgrep, and codegraph tools during the ALIGN phase to verify artifact consistency and codebase claims.
Audit Metadata