autonomous-agent-readiness
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill analyses untrusted local project files, creating an indirect prompt injection surface where malicious content in configuration files could influence the agent's assessment.\n
- Ingestion points:
scripts/discover.pyreads contents fromdocker-compose.ymland identifies file paths across the target directory.\n - Boundary markers: Absent; the discovery data is passed to the agent without delimiters or instructions to ignore embedded commands.\n
- Capability inventory: No dangerous capabilities such as subprocess calls, file-writing, or network operations were detected in the skill scripts.\n
- Sanitization: Absent; data from project files is incorporated into the agent context without escaping or validation.
Audit Metadata