money-outreach
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to research and ingest data from untrusted external sources, including LinkedIn, GitHub, Twitter, and general web search results, to identify prospects and generate personalized sales messages.
- Ingestion points: External prospect data, company signals, and social media content retrieved during the research phase described in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or safety markers to prevent the agent from following malicious instructions potentially embedded in prospect profiles or company websites.
- Capability inventory: The skill allows the agent to generate outreach content (emails) and structured data (CSV). It does not exhibit higher-risk capabilities like shell execution or direct file system writes for external data.
- Sanitization: There are no defined procedures for sanitizing or validating the content retrieved from external sources before it is interpolated into email templates or prospect lists.
Audit Metadata