clarity-gate

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the shell to run local Python scripts (scripts/claim_id.py and scripts/document_hash.py) for computing SHA-256 hashes and deterministic identifiers.
  • [PROMPT_INJECTION]: The skill operates on untrusted external documents, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Ingests external .cgd.md documents for epistemic quality verification.
  • Boundary markers: Uses standardized YAML frontmatter delimiters and a specific end marker (<!-- CLARITY_GATE_END -->) to define the scope of analyzed content.
  • Capability inventory: The skill has the ability to write files and execute shell commands for hashing, which could be targeted by adversarial instructions in processed data.
  • Sanitization: Implements canonicalization routines, including UTF-8 NFC normalization and whitespace collapsing, which provides a layer of protection against certain injection payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 04:04 PM
Security Audit — agent-trust-hub — clarity-gate