The Agent Skills Directory

[SAFE]: The skill performs legitimate analysis of caching configurations and application source code. Its purpose is to improve infrastructure performance and reliability by identifying design flaws.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it ingests local application code and caching configuration files.
Ingestion points: Uses Read, Glob, and Grep to gather context from application files.
Boundary markers: None mentioned in the instructions.
Capability inventory: Includes Bash, Write, WebFetch, and WebSearch tools.
Sanitization: No explicit sanitization or filtering of the ingested content is defined, though the context is limited to the user's local project files.

cache-recon