talent-sourcing
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute
nimbleCLI commands for web searching and data extraction. It also usespython3snippets to manage and update a local JSON business profile and memory indexes. - [EXTERNAL_DOWNLOADS]: Fetches candidate profiles and search results from external professional platforms (LinkedIn, Indeed, GitHub, Wellfound) through the Nimbleway infrastructure. These operations are performed using the vendor's own CLI tool as intended.
- [PROMPT_INJECTION]: The skill processes untrusted external data from candidate profiles which presents a surface for indirect prompt injection.
- Ingestion points: Candidate profile content is extracted in markdown format in Step 4.
- Boundary markers: No specific delimiters or safety instructions are used when passing extracted candidate data to the scoring and ranking logic in Step 5.
- Capability inventory: The skill possesses Bash, Write, and Agent tool capabilities across its main execution and sub-agents.
- Sanitization: There is no evidence of explicit sanitization or filtering of the extracted profile content before it is processed by the LLM for scoring.
Audit Metadata