get-started

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js scripts (scaffold-state.mjs and profile-strength.mjs) located within its own package to handle workspace maintenance and calculate user progress.
  • [PROMPT_INJECTION]: The skill processes user-pasted resumes, LinkedIn profiles, and job postings, which constitutes a surface for indirect prompt injection attacks. This is a standard risk for skills that analyze external data.
  • Ingestion points: External text from resumes and job postings is accepted in SKILL.md (Step 2a).
  • Boundary markers: The instructions do not define specific markers or safety delimiters for the ingested content.
  • Capability inventory: The skill can write files to the local workspace and execute internal management scripts via Node.js as described in SKILL.md.
  • Sanitization: No specific sanitization or filtering of the external input is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 02:29 PM
Security Audit — agent-trust-hub — get-started