integrate-flowlines-opencode-plugin

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill describes how to fetch session memory and inject it directly into agent prompts, which establishes a surface for indirect prompt injection.\n
  • Ingestion points: Untrusted data is retrieved via the Flowlines.getMemory() method as shown in SKILL.md.\n
  • Boundary markers: The code examples provided do not utilize delimiters or specific instructions to the AI to ignore instructions embedded within the retrieved memory.\n
  • Capability inventory: The integration leverages @opencode-ai/sdk for prompt execution and @flowlines/sdk for session and memory management.\n
  • Sanitization: No logic for sanitizing or validating the memory content is present in the provided integration snippets.\n- [EXTERNAL_DOWNLOADS]: The configuration steps guide the host environment to automatically resolve and fetch the @flowlines/opencode-plugin from the npm registry. This is a standard and expected behavior for the vendor's observability platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 04:57 PM