linkedin-sales-navigator-alt
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze data from untrusted external sources, specifically LinkedIn profiles, public activity, and company news.
- Ingestion points: Workflow steps in SKILL.md and tools referenced in references/tools-and-export.md involve reading public profiles, recent activity, and articles.
- Boundary markers: The instructions do not define delimiters or provide warnings for the agent to ignore instructions embedded within the target content.
- Capability inventory: The skill uses the agent's search and browsing tools to aggregate and format research data into lead lists.
- Sanitization: There are no instructions for sanitizing or validating the content extracted from external web pages.
Audit Metadata