docyrus-api-dev

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or safety bypass instructions were detected. The skill provides legitimate documentation for developing applications with the Docyrus platform.
  • [EXTERNAL_DOWNLOADS]: The skill references NPM packages @docyrus/api-client and @docyrus/signin. These are vendor-owned resources for the author 'docyrus' and are used for API integration and authentication.
  • [DATA_EXFILTRATION]: The skill documentation includes examples of network requests to api.docyrus.com and alpha-api.docyrus.com. These are official vendor domains required for the primary purpose of the skill and do not target sensitive local data.
  • [PROMPT_INJECTION]: The skill establishes an interface for retrieving data from external Docyrus data sources, which creates a theoretical surface for indirect prompt injection.
  • Ingestion points: Data is ingested via REST API responses from endpoints such as /v1/apps/{appSlug}/data-sources/{slug}/items as described in the documentation.
  • Boundary markers: No specific delimiters or instructions for the agent to ignore embedded commands in the retrieved data are provided.
  • Capability inventory: The @docyrus/api-client library provides full REST capabilities (GET, POST, PATCH, DELETE) to the api.docyrus.com endpoints.
  • Sanitization: No sanitization or validation of the retrieved data content is mentioned before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 11:03 AM