The Agent Skills Directory

[SAFE]: The skill logic is focused on legitimate development tasks such as analyzing project structure and generating testing templates. No obfuscation, hidden payloads, or suspicious network activities were identified in the analysis of the skill instructions or code snippets.
[INDIRECT_PROMPT_INJECTION]: The skill operates on an ingestion surface by reading and analyzing existing source code to generate test cases. 1. Ingestion points: The skill is instructed to read local project files including package.json, configuration files, and component source code. 2. Boundary markers: The instructions do not define specific delimiters or markers to warn the agent to ignore instructions embedded within the analyzed files. 3. Capability inventory: The skill's capabilities are restricted to reading workspace files for analysis and generating new test files in specified directories. 4. Sanitization: No sanitization of ingested code content is specified in the workflow. While this creates an attack surface for processing untrusted code, the skill's utility and lack of critical capabilities maintain a safe security posture.

test-generator