llm-docs-optimizer

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a local script scripts/analyze_docs.py used to identify formatting and metadata issues in documentation. The script relies on standard Python libraries (re, sys, pathlib, typing, collections) and performs no network requests or persistent system modifications.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted project documentation, which constitutes an indirect prompt injection surface.
  • Ingestion points: Documentation content from README.md and other project files is read into context via SKILL.md and analyze_docs.py.
  • Boundary markers: The skill instructs the agent to structure its output using TITLE/DESCRIPTION/CODE blocks but does not specify delimiters for separating untrusted input documentation from its own instructions.
  • Capability inventory: The agent has the ability to read project files, write optimized documentation to the workspace, and execute the provided Python analysis script.
  • Sanitization: No sanitization of input documentation content is specified before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 10:39 PM