The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted code files from the user's workspace to generate tests.
Ingestion points: Content is ingested from project files using the Read, Grep, and Glob tools mentioned in SKILL.md.
Boundary markers: The skill does not use boundary markers or specific instructions to ignore malicious content embedded in the ingested files.
Capability inventory: As defined in SKILL.md, the skill possesses the Bash, Write, and Edit capabilities, which could be leveraged if an injection occurs.
Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run unit testing frameworks (e.g., Jest, pytest, go test) and local Python utility scripts (scripts/generate_test.py, scripts/coverage_report.py) for test generation and coverage reporting.

test-automator