The Agent Skills Directory

[SAFE]: The skill is limited to text transformation based on local repository context. No malicious commands, data exfiltration patterns, or obfuscation were detected.
[INDIRECT_PROMPT_INJECTION]: The skill reads untrusted data from local repository files which could theoretically contain malicious instructions. 1. Ingestion points: CONTEXT.md, CONTEXT-MAP.md, and references/ste.md (referenced in SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: None. The skill only processes text and lacks tools for network access, file writing, or command execution. 4. Sanitization: Absent. Due to the lack of exploitable capabilities, this finding is considered safe.

simplify-this