rust-skill-creator

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard shell commands (mkdir, ls, cat) to manage skill files within the local directory ~/.claude/skills/. This behavior is strictly scoped to the skill's management and verification tasks.
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from well-known documentation repositories, specifically docs.rs and rust-lang.org, using agent-browser or WebFetch. This is the primary function of the skill and targets reputable domains.
  • [PROMPT_INJECTION]: The skill processes data from external documentation URLs to generate new skill files, representing an indirect prompt injection surface.
  • Ingestion points: External URLs processed via agent-browser or WebFetch in SKILL.md.
  • Boundary markers: None explicitly identified in the prompt templates.
  • Capability inventory: File system writes (mkdir), file reading (cat), and browser operations (agent-browser) within the skill workflow.
  • Sanitization: None identified, though the risk is mitigated by the focus on official documentation sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 05:48 PM
Security Audit — agent-trust-hub — rust-skill-creator