prompt-article-recruit

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the ingestion of untrusted data.
  • Ingestion points: Processes materials such as scenarios, pain points, and meeting minutes in SKILL.md.
  • Boundary markers: The prompt does not define clear delimiters or instruct the agent to ignore commands within the input.
  • Capability inventory: The skill includes an instruction to save files to a user-specified directory in SKILL.md.
  • Sanitization: No input sanitization or escaping mechanisms are specified, although anonymization of student names is required.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 07:33 PM