skills/kursku/skills/clarity-gate/Gen Agent Trust Hub

clarity-gate

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (scripts/claim_id.py and scripts/document_hash.py) for deterministic computations including hashing and ID generation. These operations are core to the skill's purpose of validating document integrity.
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface as it is designed to ingest and process external documents for verification, which could contain untrusted instructions.
  • Ingestion points: External documents and knowledge base files provided for verification (SKILL.md).
  • Boundary markers: The skill documentation defines structural markers like <!-- CLARITY_GATE_END --> and standardized YAML frontmatter to delimit processed content.
  • Capability inventory: The skill executes Python scripts for hashing and ID generation and generates annotated document outputs (SKILL.md).
  • Sanitization: The skill identifies formal structural rules and recommends backtick escaping for content that might otherwise be parsed as markers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 10:34 PM
Security Audit — agent-trust-hub — clarity-gate