claim-check

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script (scaffold-state.mjs) to initialize the environment. This script is part of the skill's own package and is used to ensure necessary state files are present before operation.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including user-provided resumes, CVs, and application drafts, to identify and classify claims. This ingestion represents a surface for indirect prompt injection. However, the risk is mitigated by the skill's lack of network capabilities and its highly structured processing workflow.
  • Ingestion points: Reads from my-documents/*.md and user-pasted text.
  • Boundary markers: None explicitly defined to separate data from instructions during analysis.
  • Capability inventory: The skill utilizes file system access (read/write to my-documents/) and local command execution (node).
  • Sanitization: No specific sanitization or filtering logic is mentioned for the processed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 02:29 PM
Security Audit — agent-trust-hub — claim-check