The Agent Skills Directory

[SAFE]: The skill provides a logical framework for structured debate. All instructions are transparent and consistent with the stated purpose of deliberation. No obfuscation, persistence mechanisms, or unauthorized privilege escalation attempts were found.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied queries and has access to external tools like WebSearch and WebFetch, which introduces a surface for indirect prompt injection from untrusted external content.
Ingestion points: User input via $ARGUMENTS and external data retrieved through WebSearch or WebFetch tools (referenced in SKILL.md).
Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions found within retrieved data.
Capability inventory: The skill utilizes Read, Grep, Glob, Write, WebSearch, and WebFetch to perform its tasks.
Sanitization: No explicit sanitization, filtering, or escaping logic is defined for the external content before it is processed by the 'Council' advisors.

thinking-council