stakeholder-communicator

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Risk\n
  • Ingestion points: The skill reads content from arbitrary technical documents or JSON reports specified via the input argument in src/index.ts.\n
  • Boundary markers: The implementation does not include any delimiters (e.g., XML tags or triple quotes) or specific instructions to the agent to disregard commands embedded within the source documents.\n
  • Capability inventory: The skill has filesystem access to read (fs.readFileSync) and write (safeWriteFile from the @agent/core library) files, providing an attack surface for data manipulation if the prompt logic is hijacked.\n
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the input content before it is processed by the translation and extraction logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 10:53 PM