thinking-effectuation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and provides a reasoning framework for decision-making. It does not include any scripts, shell commands, or network activity.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates a reasoning process based on user-supplied information regarding their 'means' (identity, skills, network) and 'affordable loss'.
- Ingestion points: User-provided data describing their context, resources, and goals in
SKILL.md. - Boundary markers: Absent; the procedure instructs the agent to treat user input as direct context for the effectuation brief.
- Capability inventory: No file writing, network operations, command execution, or subprocess calls are defined or referenced.
- Sanitization: None present.
- Analysis: While the skill processes untrusted user input, it lacks any powerful capabilities that could be abused via prompt injection, resulting in a safe profile.
Audit Metadata