recruit-outreach

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, security vulnerabilities, or policy violations were detected within the skill's instructions. The skill operates purely as a text generation engine for recruiting workflows.
  • [DATA_EXFILTRATION]: The skill does not use any networking tools or include hardcoded credentials. It does not attempt to access sensitive files such as SSH keys or environment variables.
  • [REMOTE_CODE_EXECUTION]: There are no patterns involving external code downloads, package installations, or shell command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data (resumes and LinkedIn profiles) which represents an ingestion surface for indirect prompt injection. However, the risk is negligible because the skill's only capability is writing a markdown file; it lacks dangerous tools (like network access or code execution) that an attacker could exploit through injected instructions. Evidence Chain: Ingestion point in SKILL.md via the candidate variable; no boundary markers present; capability limited to markdown file creation; no sanitization present.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 06:04 PM
Security Audit — agent-trust-hub — recruit-outreach