abm
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. This occurs when untrusted external data influences the agent's behavior.
- Ingestion points: Data retrieved via
enrich_company,enrich_person, andfind_person(which sources information from public domains and LinkedIn) is used as context for plan generation. - Boundary markers: The skill instructions do not define clear delimiters or include 'ignore embedded instructions' warnings when processing retrieved stakeholder or company data.
- Capability inventory: The agent has the capability to perform sensitive actions like
generate_emailandgenerate_contentusing this unverified data. - Sanitization: There is no evidence of content filtering or escaping for the research data before it is interpolated into generation prompts.
Audit Metadata