plan-camera-shots

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data for story beats and production assets, creating a surface for potential indirect prompt injection attacks. However, the risk is negligible as the skill lacks access to the file system, network, or command-line tools.\n
  • Ingestion points: payload properties in schemas/input.schema.json.\n
  • Boundary markers: Absent.\n
  • Capability inventory: None. The skill does not perform network requests, file writes, or shell operations.\n
  • Sanitization: Relies on structured JSON schema validation for input payload.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:36 AM
Security Audit — agent-trust-hub — plan-camera-shots