Skills
skills/adaptationio/skrillz/autonomous-master/Gen Agent Trust Hub

autonomous-master

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): Indirect Prompt Injection Surface.\n
  • Ingestion points: User-provided specifications from the 'autonomous start' command are parsed by scripts/command_parser.py and stored in feature_list.json.\n
  • Boundary markers: The generate_continuation_prompt function in scripts/continuation_generator.py interpolates these descriptions and steps directly into a markdown template without protective delimiters or instructions to ignore embedded instructions.\n
  • Capability inventory: According to references/COMMANDS.md, the skill has significant capabilities including file system modification and shell script execution (init.sh).\n
  • Sanitization: The validate_specification function in scripts/command_parser.py only performs basic length and keyword checks, lacking sanitization for prompt injection payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM