mdsel
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill instructions facilitate reading external markdown documentation which could contain embedded malicious instructions. \n- Ingestion points: Markdown files, README.md, and project documentation. \n- Boundary markers: Absent; there are no instructions for the agent to ignore potential instructions within the ingested data. \n- Capability inventory: Limited to read-only access via mcp__mdsel__mdsel and the Read tool. \n- Sanitization: Absent; data is read and processed as raw markdown. \n- Prompt Injection (SAFE): The skill content is strictly instructional regarding tool usage and does not attempt to bypass safety guidelines or override behavior. \n- No Code (SAFE): This skill consists entirely of markdown instructions and metadata with no associated scripts, binaries, or installation steps.
Audit Metadata