ambition
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided tasks and prompts, which serves as an ingestion point for external data that could contain indirect instructions. Ingestion points: User tasks and prompts provided via the /ambition command in SKILL.md. Capability inventory: The skill executes a local Python script for analytical purposes but does not perform network operations or sensitive file access. Boundary markers: The skill instructions mandate the creation of a 'brief' and require explicit user approval before executing the work plan, effectively limiting the scope of the agent's actions. Sanitization: No specific technical sanitization of the input strings is mentioned beyond the structural boundaries.
- [COMMAND_EXECUTION]: The skill executes a local Python utility script to assist in selecting appropriate mental models and lenses. Evidence: The skill calls python3 scripts/deal.py with user-supplied task keywords as arguments. The script is included in the skill package, uses only Python standard libraries, and does not exhibit any dangerous behaviors such as dynamic code execution or external communication.
Audit Metadata