review-skills

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to read and process untrusted instructions from other skill files.\n
  • Ingestion points: The agent is instructed to read every SKILL.md under .cursor/skills/ and any files they reference (SKILL.md).\n
  • Boundary markers: There are no delimiters or specific instructions to isolate the content of the audited skills from the agent's control logic, creating a risk that malicious instructions in a reviewed skill could override the agent's behavior.\n
  • Capability inventory: The skill possesses the capability to read any file in the codebase to verify references, which could be abused if an injection occurs (SKILL.md).\n
  • Sanitization: The instructions do not include logic to sanitize or escape the content of the files being reviewed before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 11:03 AM
Security Audit — agent-trust-hub — review-skills