baseproject-update
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches updates from the author's official repository at
https://github.com/AutumnsGrove/BaseProject.gitto ensure the project uses the latest version of the BaseProject templates. - [COMMAND_EXECUTION]: The workflow uses standard shell commands including
gitfor repository cloning and committing,cpfor file synchronization and backup creation, andrmfor removing temporary files in/tmp/bp-update. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from a remote repository to update local project instructions and skills, creating a potential surface for indirect injection if the source were compromised.
- Ingestion points: Clones external content from
github.com/AutumnsGrove/BaseProject.gitinto the local project structure (.claude/skills/,AgentUsage/,AGENT.md). - Boundary markers: The skill does not implement specific delimiters or sanitization during the merge process, relying on the user to review changes before or after the git commit step.
- Capability inventory: Includes file system write access (
cp), directory management (mkdir,rm), and version control operations (git add,git commit). - Sanitization: No automated sanitization of markdown or instruction content is performed; the skill logic focuses on structural merging and preservation of custom user content.
Audit Metadata