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.mdunder.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