snipgrapher
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute snipgrapher CLI commands for project initialization, environment validation (doctor command), and rendering operations.
- [EXTERNAL_DOWNLOADS]: The skill utilizes npx and npx --yes to fetch the snipgrapher package from the official NPM registry when the binary is not pre-installed.
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and processing local source code files (e.g., .ts, .js) to generate snippet images, creating a surface where malicious content in those files could influence agent behavior. 1. Ingestion points: Local source files referenced in SKILL.md and rules/rendering-workflows.md. 2. Boundary markers: Not present in the skill instructions. 3. Capability inventory: Includes shell execution (snipgrapher, ls, cat) and file system writes for outputting images. 4. Sanitization: No sanitization or validation of input file content is specified.
Audit Metadata