linkedin-url-lookup
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the global installation of the
deeplinepackage from the NPM registry. - [COMMAND_EXECUTION]: The skill instructions involve executing CLI commands to initialize and use the tool, including
deepline auth registeranddeepline -h. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied identity information such as name and company, which serves as an ingestion point for untrusted content.
- Ingestion points: Name and company data provided by the user in SKILL.md.
- Boundary markers: No delimiters or explicit instructions to ignore embedded content are used to isolate user data.
- Capability inventory: The skill executes the
deeplineCLI tool and reads local files via relative paths (e.g.,../deepline-gtm/recipes/). - Sanitization: There is no evidence of input validation or sanitization within the skill instructions.
Audit Metadata