emws-api

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill reads sensitive local files to facilitate API authentication and configuration.\n
  • Evidence: scripts/lib/config.ts accesses ~/.config/emws/.env for secrets, and scripts/lib/auth.ts manages cached tokens in ~/.config/emws/tokens/.\n
  • Mitigation: A dedicated redactor (scripts/lib/redact.ts) is used to mask these secrets in all console output and local log files. Additionally, the skill validates that the .env file has restricted permissions (mode 600) before reading it.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses, which could potentially contain adversarial instructions targeting the agent.\n
  • Ingestion points: API response bodies are retrieved in scripts/lib/cli.ts and passed to the agent's context.\n
  • Boundary markers: The skill does not implement specific delimiters to isolate API content from the agent's instructions.\n
  • Capability inventory: The agent can use the skill to perform HTTP requests (GET, POST, PUT, PATCH, DELETE) and record logs to the file system.\n
  • Sanitization: While credentials are redacted, the textual content of API responses is not sanitized for natural language instructions.\n- [COMMAND_EXECUTION]: The skill utilizes local shell commands to gather metadata for its logging system.\n
  • Evidence: scripts/lib/log.ts executes git branch --show-current to record the current development context in the call logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 07:57 PM