kairos-lite

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Comprehensive analysis of the skill's instructions and scripts reveals no malicious patterns, exfiltration attempts, or unauthorized command execution.
  • [COMMAND_EXECUTION]: The utility script scripts/job_spec.py is used to create JSON-formatted job specifications. It is benign, using standard Python libraries to handle user inputs without any file system or network side effects.
  • [PROMPT_INJECTION]: The skill includes a template (references/prompt-template.md) that processes external data, creating an indirect prompt injection surface. This is evaluated as safe due to the included operational constraints:
  • Ingestion points: External workspace data is ingested via the <context> placeholder in references/prompt-template.md.
  • Boundary markers: The template uses structural delimiters (e.g., <context>) to separate untrusted data from instructions.
  • Capability inventory: The skill provides a job specification generator (scripts/job_spec.py) but does not include tools for arbitrary code execution or network operations.
  • Sanitization: No explicit sanitization or filtering of the interpolated context is performed within the provided skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:50 PM