markdown-csv-reporter

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official accessibility guidelines and rule documentation from the W3C, CommonMark, and the markdownlint project on GitHub.
  • [COMMAND_EXECUTION]: The skill reads a source markdown file and writes three CSV files (findings, scorecard, and remediation plan) to the local file system. These operations are required for the tool's core functionality of report generation.
  • [PROMPT_INJECTION]: The skill ingests data from external markdown reports, which creates an indirect prompt injection surface.
  • Ingestion points: Findings are parsed from MARKDOWN-ACCESSIBILITY-AUDIT.md or user-specified report files.
  • Boundary markers: No specific delimiters are used to wrap or isolate the untrusted content being processed.
  • Capability inventory: The skill is capable of writing files to the current working directory.
  • Sanitization: The skill implements standard CSV quoting and escaping for output but does not sanitize the input content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 05:34 AM
Security Audit — agent-trust-hub — markdown-csv-reporter