The Agent Skills Directory

[SAFE]: The skill provides clear instructions for a collaborative exploration workflow without requesting elevated privileges, performing suspicious network operations, or hardcoding credentials. It correctly references vendor-owned resources like 'ts-principles' and 'ts-technical-writing' for its operations.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process untrusted repository content.
Ingestion points: Files in the repository, documentation, and external references are loaded into the agent context during the LOAD_CONTEXT step.
Boundary markers: None identified; the instructions do not explicitly instruct the agent to ignore instructions found within processed files.
Capability inventory: The skill can spawn sub-agents (such as ts-technical-writing) and write design artifacts to the docs/designs/ directory.
Sanitization: No explicit sanitization or filtering of the ingested content is described.
Conclusion: This surface is inherent to the skill's purpose as an exploration and synthesis tool, and no malicious patterns targeting this surface were detected.

ts-explore