diataxis
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process user-provided documentation for classification and improvement.
- Ingestion points: User input provided when the agent is asked to "improve documentation, restructure docs, or classify existing content."
- Boundary markers: Absent. The
SKILL.mddoes not specify the use of delimiters or instructions to ignore embedded commands within the processed text. - Capability inventory: No risky capabilities (subprocess, exec, network, or file-write) were detected across the skill files.
- Sanitization: Absent. The skill provides logical rules for documentation structure but does not include sanitization logic for input data.
- [No Code] (SAFE): The skill consists entirely of Markdown files for use as agent context. No scripts, binaries, or configuration files for code execution are present.
Audit Metadata