medical-billing
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to read and analyze an untrusted codebase ("actual codebase") without using boundary markers (such as XML tags or specific delimiters) or instructions for the agent to ignore embedded commands. This vulnerability allows an attacker to influence the agent's behavior by placing malicious instructions within code comments or documentation in the target project.
- Ingestion points: Codebase files identified in Phase 0 and analyzed throughout the process.
- Boundary markers: Absent. The skill does not define delimiters to separate its instructions from the codebase data.
- Capability inventory: Reading and analyzing project files, file system navigation, and appending execution metadata to
skill-telemetry.mdin the~/.claude/projects/directory. - Sanitization: Absent. The skill does not specify any sanitization or validation for the content retrieved from external project files.
Audit Metadata