Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the '@linkedapi/linkedin-cli' package from the official NPM registry to enable LinkedIn automation features.
- [COMMAND_EXECUTION]: The skill uses the 'linkedin' CLI to execute operations such as searching profiles, sending messages, and creating posts.
- [PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection through its data processing functions:
- Ingestion points: The skill retrieves untrusted content from LinkedIn profiles, messages, and posts using commands like 'linkedin person fetch' and 'linkedin message get' (SKILL.md).
- Boundary markers: There are no instructions or templates provided to wrap retrieved LinkedIn content in delimiters to prevent the agent from obeying instructions embedded in that data.
- Capability inventory: The agent can perform significant actions such as sending messages, creating posts, and running custom workflows via 'linkedin workflow run' (SKILL.md).
- Sanitization: The skill does not describe any validation or filtering of content retrieved from LinkedIn before it is presented to the agent.
Audit Metadata