Skills
skills/pakco77/pakco-skills/knowledge-peak-map/Gen Agent Trust Hub

knowledge-peak-map

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses python3 to run internal scripts (render_territory_demo.py and self_check.py) for processing document metadata and generating visualization files. These operations are restricted to the local filesystem within the user-specified scope.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the skill via the skills CLI from the author's GitHub repository (pakco77/pakco-skills). This is a standard installation mechanism and uses a resource belonging to the skill's author.
  • [PROMPT_INJECTION]: The skill's primary function involves analyzing user-provided Markdown content to extract semantic rules. This ingestion of external data represents a surface for indirect prompt injection, where maliciously crafted notes could attempt to bias the rule extraction. However, the risk is limited to the generated map output, and the skill includes basic HTML escaping in its renderer to mitigate cross-site scripting risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 06:33 AM
Security Audit — agent-trust-hub — knowledge-peak-map