state-management-expert
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
SKILL.mdfile defines a mandatory 'Memory Protocol' that instructs the agent to use theBashtool to execute the commandcat .claude/context/memory/learnings.mdfor context management. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) as it is designed to analyze untrusted code using high-privilege tools.
- Ingestion points: Code files provided via the
targetparameter in theinput.schema.json. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill's guidelines.
- Capability inventory: The skill utilizes
Bash,Write,Edit,Read,Grep, andGlobtools. - Sanitization: The skill does not implement sanitization or validation of the analyzed code before it is processed in the tool-enabled environment.
Audit Metadata