rust-skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because its core purpose is to ingest untrusted external documentation to generate executable skill files.
  • Ingestion points: Processes content from arbitrary user-provided URLs and constructed paths to docs.rs and rust-lang.org as described in Step 1 and Step 3.
  • Boundary markers: Absent; the workflow does not specify delimiters or instructions to ignore malicious content embedded within the documentation files.
  • Capability inventory: The skill leverages /create-llms-for-skills and /create-skills-via-llms which have the capability to parse external data and write new skill configurations to the local filesystem at ~/.claude/skills/.
  • Sanitization: No sanitization, escaping, or validation of the documentation content is performed before it is used to generate new agent instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM