Lead Gatherer Skill
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill performs research on external websites, which creates a surface for indirect prompt injection where an attacker could place malicious instructions on a webpage to influence the agent's behavior.
- Ingestion points: External company websites and background verification sources (identified in SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or specific warnings to ignore instructions found within the researched content.
- Capability inventory: The skill writes processed data to CSV files in the
/agent/directory. - Sanitization: The skill mentions stripping PII and avoiding hallucination, but it lacks specific mechanisms to sanitize or escape instructional content found in external research data.
Audit Metadata