The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns, prompt injections, or obfuscated code were detected. The skill is purely informational, providing the agent with paths to additional documentation.
[DATA EXPOSURE] (SAFE): While the skill references local file paths (e.g., <cc-polymath-root>/skills/caching/), these are limited to the skill's own directory structure and do not target sensitive system files or credentials.
[INDIRECT PROMPT INJECTION] (SAFE): The skill creates an ingestion surface by instructing the agent to read external markdown files. However, because the skill lacks exploitable capabilities (such as network access, file writing, or command execution), this surface does not pose a significant risk.
Ingestion points: INDEX.md and various caching strategy files referenced in the Available Skills section.
Boundary markers: Absent in this gateway file.
Capability inventory: No high-risk capabilities detected.
Sanitization: Not applicable for this discovery-only skill.

discover-caching