linkedin-outreach
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's logic is focused on legitimate professional networking and personalization strategies. It does not contain any suspicious scripts, credentials, or persistence mechanisms.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external data from LinkedIn profiles via the
WebFetchtool. - Ingestion points: LinkedIn profile URLs or content extracted in Step 1 (SKILL.md).
- Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore embedded commands within the fetched profile text.
- Capability inventory:
WebFetch,WebSearch, and integration with other skills likelead-qualification. These are read-focused or logical tools and do not represent a high-risk capability tier (such as file-system writes or arbitrary command execution). - Sanitization: Absent. There is no explicit instruction to sanitize or escape the content retrieved from external URLs.
Audit Metadata