find-email-by-name

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [DATA_EXPOSURE]: The skill accesses the sensitive file path ~/.gooseworks/credentials.json to retrieve authentication tokens. This information is used exclusively to authenticate requests to the service's own backend at api.gooseworks.ai.
  • [COMMAND_EXECUTION]: Setup instructions include the use of python3 to parse JSON credentials from the local file system.
  • [EXTERNAL_DOWNLOADS]: The documentation references npx gooseworks login, which involves fetching and executing a package from the npm registry, an established and well-known service.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes data from external APIs.
  • Ingestion points: API response data from Hunter and Tomba as defined in SKILL.md.
  • Boundary markers: None are present to delimit external data from agent instructions.
  • Capability inventory: The skill uses curl for network communication; no file-system modification, privilege escalation, or dynamic code execution capabilities are present.
  • Sanitization: No explicit sanitization of external API data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 06:17 AM
Security Audit — agent-trust-hub — find-email-by-name