skills/reddb-io/red-skills/wiki/Gen Agent Trust Hub

wiki

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions specify the use of local command-line utilities such as pdftotext for PDF-to-text conversion and grep or ripgrep for searching stored markdown files.
  • [EXTERNAL_DOWNLOADS]: The skill performs external network operations using WebFetch to retrieve web page content and downloads associated image assets to the local repository.
  • [PROMPT_INJECTION]: By ingesting data from external URLs and PDF files, the skill presents an indirect prompt injection surface.
  • Ingestion points: External data enters the context via WebFetch and PDF extraction as described in SKILL.md.
  • Boundary markers: The skill uses YAML frontmatter headers and predefined markdown templates to separate metadata from body content.
  • Capability inventory: The skill combines filesystem write access, network retrieval, and local command execution capabilities.
  • Sanitization: External inputs used in filenames are sanitized via slugification, and content is normalized to markdown before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 05:33 PM
Security Audit — agent-trust-hub — wiki