storyblok-use-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions in references/assets.md direct the agent to execute a shell command using Bash that is returned by the mcp__storyblok__upload_asset tool.
- [EXTERNAL_DOWNLOADS]: The skill guides the agent to use curl to download files from Storyblok's asset storage (a.storyblok.com) to local paths for the purpose of generating descriptive alt-text.
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where malicious content stored in Storyblok could attempt to influence agent behavior. * Ingestion points: Data is ingested via getStoryById, listStories (references/stories.md), and listAssets (references/assets.md). * Boundary markers: No specific delimiters or safety instructions are defined to separate ingested data from agent commands. * Capability inventory: The agent has access to generic executors for creating, updating, and deleting content (execute_mutating, execute_destructive), as well as shell execution (bash). * Sanitization: No sanitization or validation logic is prescribed for data retrieved from the Storyblok API.
Audit Metadata