The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and interpret external session reports and artifacts (JSON, text, and .codex files). While this creates a surface for indirect prompt injection if the processed data contains malicious instructions, the skill includes explicit guidelines to minimize this risk, such as reconciling multiple sources, redacting sensitive content, and avoiding raw reproduction of data.
[SAFE]: The skill consists entirely of instructional text and configuration. It does not perform network operations, file system modifications (beyond reading authorized reports), or code execution. It explicitly instructs the agent to avoid unauthorized data movement and to respect organizational security policies.

session-analysis