develop-timeline-studio-plugin

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the integration of third-party provider APIs and SDKs into a core application, creating a potential attack surface for untrusted external data.
  • Ingestion points: External provider documentation, API response payloads, and browser SDKs as described in SKILL.md.
  • Boundary markers: The instructions in SKILL.md explicitly mandate the use of an "isolated adapter" and a "declarative manifest" to maintain strict boundaries between providers and the editor core.
  • Capability inventory: The skill involves modifying source code files (e.g., src/components/GenerationPlugins.jsx) and executing build toolchains (npm run build) as noted in SKILL.md.
  • Sanitization: Implementation requirements in SKILL.md include converting raw transport failures into localized errors without leaking secrets and performing media validation before reporting completion.
  • [COMMAND_EXECUTION]: The instructions in SKILL.md direct the agent to execute local development tools, including npm run lint, npm run typecheck, and npm run build, to validate the implementation of new connectors.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 04:21 PM
Security Audit — agent-trust-hub — develop-timeline-studio-plugin