code-clone-assistant
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill incorporates a self-modification mechanism. In the 'Self-Evolving Skill' section of
SKILL.md, the agent is instructed to 'fix this file immediately' if it encounters errors or needs workarounds. This allows the agent to rewrite its own instructions and behavior based on runtime data without a separate deployment process. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the user's codebase to perform its primary function, which creates a potential injection surface.
- Ingestion points: The agent reads local project files and the output of analysis tools (
pmd-cpd.mdandsemgrep.sarif) inreferences/complete-workflow.md. - Boundary markers: The instructions do not specify the use of XML tags or other delimiters to isolate untrusted code content from the agent's instructions during analysis.
- Capability inventory: The skill utilizes
Bash,Edit, andWritetools, granting it the ability to modify the filesystem and execute arbitrary code based on the results of its analysis. - Sanitization: There is no explicit sanitization or validation of the code clones detected before they are analyzed for refactoring.
Audit Metadata