The Agent Skills Directory

[SAFE]: The skill functions as a logical coordinator for research pipelines and does not contain any evidence of malicious code, obfuscation, or unauthorized data access.
[COMMAND_EXECUTION]: The skill utilizes a local Python script scripts/passport.py to calculate the next gate and routing for analysis modules. The script is implemented using the Python standard library, uses argparse for safe command-line parsing, and validates all inputs against fixed internal lists of allowed stages and design types.
[DATA_EXPOSURE]: No sensitive file paths, environment variables, or hardcoded credentials were found in the instructions or the supporting script.
[INDIRECT_PROMPT_INJECTION]: The skill processes a YAML 'Design Passport' which is an ingestion point for external data. However, the risk is minimal as the supporting script passport.py does not use unsafe deserialization or execution functions (like eval or exec) and strictly maps inputs to a predefined methodology spine.

alterlab-ssci-orchestrator