The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external code files to generate test logic without defined boundary markers or sanitization.
Ingestion points: The skill reads source code and project files using the Read, Grep, and Glob tools as part of its test generation workflow.
Boundary markers: Absent. The skill does not instruct the agent to ignore instructions embedded within the code being analyzed (e.g., inside comments or strings).
Capability inventory: The skill has the ability to modify files via Write and Edit tools and execute shell commands via the Bash tool.
Sanitization: None identified. External code content is interpolated into the agent's context without escaping or validation.

backend-test