linkedin-content
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes the
tavily/search-assistanttool to research viral LinkedIn patterns from the web. This process involves ingesting untrusted third-party content into the agent's context. - Ingestion points: The
SKILL.mdfile defines a research workflow usingbelt app run tavily/search-assistantto query external web data. - Boundary markers: No explicit delimiters or system instructions are provided to the agent to treat the search results as untrusted or to ignore embedded instructions within them.
- Capability inventory: The skill is granted
Bash(belt *)access, allowing it to execute CLI tools, manage logins, and trigger other applications likex/post-createandinfsh/html-to-image. - Sanitization: There is no evidence of content sanitization or filtering applied to the search results before they are processed by the agent for pattern analysis.
Audit Metadata