skill-doctor
Warn
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a shell command
ai-skillet doctor "$ARGUMENTS"where$ARGUMENTScontains user-provided input. If the input is not strictly validated or sanitized by the host platform, it could allow for arbitrary command execution via shell metacharacters such as semicolons, pipes, or backticks. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and audit local files (skill catalogs and metadata). This creates an attack surface where malicious instructions embedded in the analyzed files could influence the agent's behavior.
- Ingestion points: Local file system paths provided via the
--rootargument in SKILL.md. - Boundary markers: None specified in the instructions for parsing audit results.
- Capability inventory: Shell command execution via the
ai-skillettool as defined in SKILL.md. - Sanitization: The skill does not perform its own sanitization of the file content before processing or reporting findings.
Audit Metadata