ln-43-code-modernizer
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze arbitrary repository code, which could contain malicious instructions or payloads designed to influence the agent's behavior. The skill also calls for the execution of repository-defined scripts for building and testing, creating a vector for command execution based on untrusted data.
- Ingestion points: Source code files, git metadata, and package manifests as specified in the checklist in SKILL.md.
- Boundary markers: The skill lacks explicit instructions or markers to distinguish between its own instructions and untrusted data analyzed from the target repository.
- Capability inventory: The checklist includes running build, lint, test, and packaging commands, as well as using native package managers.
- Sanitization: No sanitization or safety checks are prescribed for the repository code before it is analyzed or its scripts are executed.
Audit Metadata