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