sui-move-review
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. 1. Ingestion points: It reads untrusted Move source code, package manifests, and repository-specific instructions as specified in the review process (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious directions embedded within the audited code. 3. Capability inventory: The skill directs the agent to run build, lint, test, and coverage gates (SKILL.md, Step 7). 4. Sanitization: No sanitization or validation of the ingested repository content is mentioned before it is processed or executed.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute build, lint, and test tools based on the target repository's pinned configurations (SKILL.md, Step 7). While this is a standard requirement for auditing, it grants the agent the capability to run repository-defined commands, which could be malicious if the repository itself is untrustworthy.
Audit Metadata