oneshot-local

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides documentation and examples for using the official @oneshot-agent/sdk to perform local business searches and data resolution. All referenced resources, including the SDK and documentation links, belong to the verified vendor 'oneshot-agent'.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the @oneshot-agent/sdk Node.js package. This is a standard dependency for accessing the vendor's local business discovery services and follows established integration patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from business directories into the agent's context.
  • Ingestion points: External business data such as names, categories, and addresses enter the agent's context through the agent.localSearch and agent.localResolve methods defined in SKILL.md.
  • Boundary markers: The provided documentation does not explicitly define delimiters or specific safety instructions for handling the retrieved business data.
  • Capability inventory: The skill uses high-level SDK methods and does not demonstrate high-risk capabilities such as arbitrary command execution, file system modifications, or persistence mechanisms.
  • Sanitization: The documentation does not describe specific sanitization or filtering logic for the external business information being retrieved.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 06:34 PM