cs-resync-codebase
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses vendor-specific tools and standard git commands for its operations. All external resources, such as the
@codespring-app/clipackage, are associated with the skill's author context. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it analyzes untrusted data from the codebase (source files and git history) to update documentation.
- Ingestion points: Reads file content and git logs from the local repository.
- Boundary markers: No delimiters are used to wrap the ingested codebase data to prevent the agent from following instructions found within the code.
- Capability inventory: The skill can update documentation in the CodeSpring service via CLI but is restricted to read-only access on the application codebase.
- Sanitization: There is no evidence of sanitization or filtering of the codebase data before it is processed by the agent.
Audit Metadata