The Agent Skills Directory

[SAFE]: No malicious patterns such as data exfiltration, obfuscation, or persistence mechanisms were detected. The skill focuses on standard software engineering practices for debugging.
[NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts, binaries, or configuration files that could hide malicious logic.
[PROMPT_INJECTION]: The skill describes a process that involves an indirect prompt injection surface by consuming external debug data.
Ingestion points: The workflow instructs the agent to capture and treat supplied logs, stack traces, and screenshots as evidence (SKILL.md).
Boundary markers: No explicit delimiters or boundary instructions are provided to separate debug data from agent instructions.
Capability inventory: The agent is authorized to edit code and execute shell commands to reproduce and verify fixes (SKILL.md).
Sanitization: There are no mentions of sanitizing or escaping the content of logs or traces before they are processed by the agent.

ts-debug