The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as code, configuration files, and documentation to identify 'footguns'. This creates a theoretical surface for indirect prompt injection where malicious instructions could be embedded in the reviewed content. However, the skill is explicitly defined as a 'read-only review lens' and lacks tools for network access, file writing, or command execution, which effectively mitigates the risk of actionable exploitation.
[SAFE]: The skill consists entirely of instructional text and a configuration file. It does not include scripts, binaries, or references to untrusted external resources.

footgun-finder