The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files, specifically TestResults.xml and ProjectVersion.txt, which could be influenced by a malicious actor or a compromised project. The extracted failure messages and stack traces are directly used by the agent to generate analysis and reports without sanitization or clear boundary markers.
Ingestion points: TestResults.xml parsed in scripts/parse-test-results.js (Step 5) and ProjectVersion.txt read in SKILL.md (Step 2).
Boundary markers: Absent. The skill instructions do not specify using delimiters or warnings when processing the content of these files.
Capability inventory: The skill uses the Bash tool to execute shell commands, the Read tool for file access, and node to run helper scripts.
Sanitization: No sanitization or escaping is performed on the test failure messages or stack traces before they are presented for analysis in Step 6 and 7.
[COMMAND_EXECUTION]: The skill builds and executes shell commands to run the Unity Editor and several helper scripts. While this is the primary purpose of the skill, it involves interpolating paths like unityPath and projectPath into shell strings.
Evidence: SKILL.md Steps 1, 4, and 5 demonstrate executing node scripts and the Unity.exe (or platform equivalent) binary with multiple command-line arguments via the Bash tool.

unity-test-runner