skills/pinecone-io/cultivar/cultivar/Gen Agent Trust Hub

cultivar

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the cultivar CLI to perform tasks such as init, run, grade, and report, which are standard operations for its stated purpose of agent evaluation.
  • [COMMAND_EXECUTION]: Task configuration files (tasks/*.yaml) allow for optional shell hooks (setup, teardown, verify) to be executed during the test lifecycle.
  • [EXTERNAL_DOWNLOADS]: The tool can fetch and cache documentation from external http(s):// URLs specified in the context_refs or self_navigate_refs fields of a task.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.
  • Ingestion points: URLs in context_refs and self_navigate_refs, and intent fields in tasks/*.yaml.
  • Boundary markers: None explicitly mentioned in the skill documentation; users are advised to use --dry-run for inspection.
  • Capability inventory: Execution of shell commands via cultivar and network requests to LLM providers.
  • Sanitization: None described in the instructions beyond manual review using --dry-run.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 07:31 PM