start-flutter-craft
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs extremely forceful and imperative language designed to override the agent's standard decision-making processes. Phrases such as 'YOU DO NOT HAVE A CHOICE,' 'ABSOLUTELY MUST,' 'This is not negotiable,' and 'You cannot rationalize your way out of this' are used to ensure the agent follows the specified workflow without exception.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a high-sensitivity trigger for tool invocation, instructing the agent to call the 'Skill' tool if there is even a '1% chance' a skill might apply, before providing any response or clarifying questions. This increases the risk of malicious user input triggering tool execution prematurely.
- Ingestion points: The primary ingestion point is the 'User message received' mentioned in the workflow logic within SKILL.md.
- Boundary markers: The skill does not define any specific delimiters or instructions to ignore embedded commands within the user messages it processes.
- Capability inventory: The skill mandates the invocation of the 'Skill' tool (
flutter-craft:*) based on these inputs. - Sanitization: There is no evidence of input validation or sanitization before the decision to invoke sub-skills is made.
Audit Metadata