finding-dev-server-url
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process the full content of terminal log files, which are external, untrusted data sources. This creates a surface for indirect prompt injection attacks if terminal output contains malicious text patterns.
- Ingestion points: Terminal output logs located at
<terminals_folder>/<id>.txtare read entirely by the agent. - Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or to ignore potential instructions embedded within the terminal text.
- Capability inventory: The agent has the ability to list files (
ls), read file contents, and control a browser (browser_navigate,browser_take_screenshot). - Sanitization: There is no evidence of sanitization, filtering, or validation of the terminal content before it is processed by the agent's reasoning engine.
Audit Metadata