direct-messages

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes incoming messages from X/Twitter, which serve as untrusted external inputs. This creates a surface for indirect prompt injection where malicious instructions embedded in DMs could manipulate the agent's actions.\n
  • Ingestion points: src/dmManager.js reads conversation content and message requests.\n
  • Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: The skill can send personalized DMs and export conversation history.\n
  • Sanitization: There is no evidence of content sanitization or validation before processing message data.\n- [NO_CODE]: The skill references source files src/sendDirectMessage.js and src/dmManager.js which contain the executable logic for interacting with the browser's DOM. These files are missing from the provided content, limiting the analysis to the metadata and documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:54 AM