manufacturing-intelligence
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill contains no executable scripts, binaries, or active code, consisting entirely of markdown documentation and YAML configuration files.
- [SAFE] (SAFE): No patterns of prompt injection, obfuscation, or privilege escalation were detected. The skill-snitch-report.md file contains a self-referential verdict which was ignored in favor of objective analysis.
- [DATA_EXFILTRATION] (SAFE): No network-capable tools, hardcoded credentials, or sensitive file paths were found.
- [INDIRECT_PROMPT_INJECTION] (LOW): 1. Ingestion points: The SKILL.md file defines the
read_filetool and references relative paths to external skills. 2. Boundary markers: Absent for cross-skill file reading. 3. Capability inventory: The skill is restricted to file reading with no shell, dynamic execution, or network sinks. 4. Sanitization: Absent. The surface is theoretical due to the lack of dangerous sinks.
Audit Metadata