fondo-debug-bundle

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API endpoints (api.fondo.com) to generate diagnostic reports, creating a surface for indirect prompt injection if the API source were to be compromised.
  • Ingestion points: The bash collection script in SKILL.md fetches JSON data from api.fondo.com/v1/compliance/status, api.fondo.com/v1/integrations, and api.fondo.com/v1/filings.
  • Boundary markers: The skill provides explicit instructions in the 'Instructions' and 'Error Handling' sections for users to review generated files for sensitive information and redaction before sharing the bundle.
  • Capability inventory: The skill utilizes curl for data retrieval, jq for parsing JSON payloads, and grep for searching log files.
  • Sanitization: No automated sanitization or schema validation is performed on the data retrieved from the remote API before processing.
  • [SAFE]: The skill uses environment variables (FONDO_API_KEY) to handle sensitive credentials, which is a recommended security practice for secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:44 AM
Security Audit — agent-trust-hub — fondo-debug-bundle