The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown instructions and does not include any Python scripts, Node.js modules, or binary executables.
[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The instructions follow standard UX research methodologies.
[DATA_EXFILTRATION]: No network operations (such as curl, wget, or fetch) or hardcoded credentials were found.
[PROMPT_INJECTION]: The instructions use natural language for task-specific guidance without attempting to override system safety filters or ignore previous instructions.
[REMOTE_CODE_EXECUTION]: There are no patterns indicating the download or execution of remote scripts.
[COMMAND_EXECUTION]: No shell commands or subprocess calls are present in the instruction set.
[SAFE]: Regarding indirect prompt injection (Category 8):
Ingestion points: The skill instructions in SKILL.md suggest reading user-provided interview transcripts and survey data.
Boundary markers: Not present.
Capability inventory: No capabilities (file writing, network access, or command execution) are present in the skill.
Sanitization: Not present.
Conclusion: While the skill processes external data, it lacks any exploitable capabilities, posing no security risk.

empathy-map