test-case-writer
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill specifies a file saving pattern at
test-cases/<id>-<slug>.md. The interpolation of user-controlled identifiers (id,slug) into the file path without sanitization instructions presents a potential path traversal surface. - [PROMPT_INJECTION]: The skill processes untrusted scenario descriptions to generate persistent test case documents, introducing a surface for indirect prompt injection.
- Ingestion points: Scenario data from
scenario-mapperrows and plain language descriptions as described inSKILL.md. - Boundary markers: The instructions do not define delimiters or protective prompts to isolate external content.
- Capability inventory: The skill is designed to write persistent markdown files to the local file system.
- Sanitization: No input validation or content escaping is specified for the ingested data.
Audit Metadata