cli-anything-inkscape

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires installing the cli-anything-inkscape Python package, which is a vendor-aligned dependency for the HKUDS author context.\n- [COMMAND_EXECUTION]: The skill performs its primary functions by executing shell commands through the cli-anything-inkscape utility.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes external data that could contain malicious instructions.\n
  • Ingestion points: The agent reads project state from project.json and manipulates SVG data through various subcommands (SKILL.md).\n
  • Boundary markers: There are no specified delimiters or system-level instructions provided to the agent to ignore instructions embedded within the processed SVG or JSON data.\n
  • Capability inventory: The skill provides full shell execution access to the cli-anything-inkscape toolset, allowing for broad document modification (SKILL.md).\n
  • Sanitization: The skill instructions do not specify any validation or sanitization protocols for the data ingested from the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 01:43 PM