skedulo-api-developer

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill provides instructions and patterns for fetching and processing platform data (e.g., Jobs, Contacts), creating a surface for indirect prompt injection if the ingested data contains malicious instructions.
  • Ingestion points: Data is retrieved via graphqlService.query, queryByPages, and newQueryBuilder as documented in SKILL.md and references/quick-reference.md.
  • Boundary markers: The provided code patterns do not include explicit boundary markers or instructions for the agent to ignore instructions embedded within the data records.
  • Capability inventory: The skill documents capabilities to modify data and communicate externally via graphqlService.mutate, mobileNotificationClient.send, and mobileNotificationClient.sendSMS (SKILL.md, references/api-clients.md).
  • Sanitization: There are no specific sanitization or validation patterns demonstrated for handling text-based fields from the retrieved records.
  • [COMMAND_EXECUTION]: Documents the use of platform-specific clients to execute GraphQL queries, mutations, and generic HTTP requests to the Skedulo API endpoints.
  • [DATA_EXFILTRATION]: Describes the use of notification and file services (mobileNotificationClient, filesClient) which allow for the movement of data via SMS or file uploads.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 11:00 AM