integrations

Warn

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script using the command python3 scripts/connector-status.py --action status to retrieve integration data. This script is part of the skill package authored by indranilbanerjee.
  • [CREDENTIALS_UNSAFE]: The process involves reading the .mcp.json configuration file and system environment variables. Accessing these sources is a risk as they are standard locations for sensitive API keys, tokens, and authentication credentials for third-party services.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes data from external, potentially untrusted configuration sources.
  • Ingestion points: System environment variables and the .mcp.json configuration file.
  • Boundary markers: None. The skill does not use delimiters or instructions to ignore instructions embedded within the connector metadata.
  • Capability inventory: The skill executes local shell commands via the connector-status.py script.
  • Sanitization: No sanitization or validation of the retrieved configuration data is performed before displaying it in the dashboard output.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 01:02 PM