Skills
Navigate
skills/aigne-io/doc-smith-skills/doc-smith-check/Gen Agent Trust Hub

doc-smith-check

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted document content (HTML and Markdown) from the local workspace to perform validation.
  • Ingestion points: The skill reads file contents from dist/ and docs/ directories, as well as planning/document-structure.yaml in scripts/validate-content.mjs and scripts/validate-structure.mjs.
  • Boundary markers: No explicit delimiters or instructions are used to separate untrusted data from processing logic.
  • Capability inventory: The skill has the capability to delete files and folders via scripts/clean-invalid-docs.mjs and execute Node.js scripts.
  • Sanitization: Validation is performed via regex and YAML parsing without explicit sanitization of the content before it influences file system operations.
  • [DATA_EXFILTRATION]: The skill performs network requests to verify the accessibility of remote images.
  • Network operations: The checkRemoteImage function in scripts/validate-content.mjs executes HTTP HEAD requests to arbitrary URLs found within document content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 11:59 AM