ln-160-docs-skill-extractor

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted content from project documentation (docs//*.md, tests/manual//*) to generate command files, presenting an indirect prompt injection surface. A malicious document could attempt to influence the logic of the generated commands.\n
  • Ingestion points: Scans markdown documentation and test files (SKILL.md Phase 1).\n
  • Boundary markers: Employs procedural classification scoring (references/procedural_extraction_rules.md) but does not define explicit prompt delimiters for ingested content.\n
  • Capability inventory: Orchestrates the creation of executable markdown files under the .claude/commands/ directory.\n
  • Sanitization: Implements a mandatory Phase 3 User Approval Gate, requiring explicit confirmation of the extraction plan before delegating file creation to worker skills.- [COMMAND_EXECUTION]: The skill is designed to create executable command files in the project's command directory. This behavior is the intended primary functionality described in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 06:29 AM