extract-skill

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): Vulnerable to Indirect Prompt Injection (Category 8).
  • Ingestion points: The skill ingests the current conversation history and existing SKILL.md files as data sources.
  • Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore embedded malicious instructions within the conversation being distilled.
  • Capability inventory: The skill has the capability to write and update files in ~/.cursor/skills/ and .cursor/skills/ (Phase 5: Write and Verify).
  • Sanitization: Absent. There is no validation or sanitization of the distilled content to ensure it does not contain malicious agent instructions.
  • DATA_EXPOSURE (SAFE): While the skill accesses the user's home directory (~/.cursor/skills/), this is limited to the skill's primary stated purpose of managing agent behaviors and does not involve unauthorized sensitive file access or exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM