chromatic-troubleshoot-config
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data provided by the user, such as error logs and configuration files, which presents a surface for indirect prompt injection.
- Ingestion points: Error messages,
.storybook/main.*,.storybook/preview.*, andpackage.jsonfiles are consumed during the troubleshooting workflow (found in SKILL.md and template.md). - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the ingested data, though it mandates a structured 'Diagnosis Card' output format.
- Capability inventory: The skill's defined operations are limited to read-only repository probes (find and grep) as listed in
reference/command-catalog.md. - Sanitization: No explicit sanitization or escaping of external content is defined.
- [COMMAND_EXECUTION]: The skill uses local shell commands to probe the repository state.
- Evidence: The
reference/command-catalog.mdfile contains bash commands (find,grep) used to locate Storybook configuration, discover story files, and inspect package dependencies. These commands are non-destructive and scoped to the project directory.
Audit Metadata