talent-sourcing
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes profile data from LinkedIn and GitHub, which are external, user-controlled sources.\n
- Ingestion points: Profile data is retrieved via
linkedin_web_v2_user_profileandstrale_github_user_profileas defined inSKILL.md.\n - Boundary markers: Absent; the instructions in
SKILL.mddo not specify the use of delimiters for external content.\n - Capability inventory: Capabilities are limited to read-only API data retrieval through the SandBase gateway tools listed in
SKILL.md.\n - Sanitization: Absent; no data sanitization steps are defined for handling content from external sources.\n- [NO_CODE]: The skill contains only markdown documentation and mapping files, with no executable scripts or external software dependencies.\n- [SAFE]: The skill follows best practices for read-only research and lacks any dangerous command execution, data exfiltration, or persistence mechanisms.
Audit Metadata