vision
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands to manage repository changes. Specifically, it executes
git addandgit committo save documentation updates to the filesystem. These actions are only performed after the user provides confirmation through theAskUserQuestiontool, and the commit message is hardcoded to prevent injection. - [INDIRECT_PROMPT_INJECTION]: The skill processes content from various project files to inform its generation, which represents a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill reads
CONTEXT.md,README.md,package.json, and other documentation files as defined in theSKILL.mdworkflow. - Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" warnings for the content read from these files.
- Capability inventory: The skill possesses the ability to execute git-related shell commands.
- Sanitization: The skill does not mention specific sanitization or escaping of the gathered project data before it is interpolated into the agent context.
Audit Metadata