apollo-data-handling

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data such as contact information and subject access requests, which creates an attack surface for indirect prompt injection.
  • Ingestion points: Data enters the system through functions like handleSubjectAccessRequest and recordConsent in references/implementation-guide.md.
  • Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore embedded commands within the ingested data.
  • Capability inventory: The skill's execution environment is granted broad capabilities via Bash(kubectl:*), Bash(curl:*), and Write tools.
  • Sanitization: While the guide includes schema validation with zod and PII hashing for logs, it lacks measures to prevent the execution of malicious natural language instructions hidden in data fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 04:40 PM