career-changer-translator

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration vectors were detected. The skill operates entirely within the agent's conversational context.
  • [NO_CODE]: The skill consists of Markdown instructions and JSON evaluation data. It does not include any scripts (Python, JavaScript, Shell) or dependencies that could be executed in the host environment.
  • [DATA_EXFILTRATION]: No network tools are requested in the frontmatter, and no URLs targeting non-whitelisted or suspicious domains are present in the text.
  • [PROMPT_INJECTION]: The instructions do not contain attempts to override system prompts or bypass safety guardrails. It follows standard instructional patterns for role-playing a career coach.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests user-provided career history (an untrusted input surface), the lack of any executable capabilities (no file writes, no network calls, no shell execution) makes this surface non-exploitable for security purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 10:02 AM
Security Audit — agent-trust-hub — career-changer-translator