hipaa

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses the $ARGUMENTS variable directly within instructions that set an 'AUTONOMOUS MODE' and command the agent to 'Do NOT ask questions.' This creates a surface where user-supplied input could potentially override the intended audit process.
  • [DATA_EXFILTRATION]: The skill includes a 'Self-Evolution Telemetry' feature that attempts to append execution metadata to ~/.claude/projects/skill-telemetry.md. Accessing and modifying files in the user's home directory (~/) outside of the immediate project workspace is a data access concern.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it is designed to systematically read and process an entire codebase, which is untrusted data.
  • Ingestion points: The audited codebase (all files in the current working directory) and the $ARGUMENTS input.
  • Boundary markers: The instructions lack explicit boundary markers or 'ignore embedded instructions' warnings when processing the target codebase.
  • Capability inventory: The skill has the capability to read any file in the repository and append content to a telemetry file in the home directory.
  • Sanitization: There is no evidence of sanitization or validation of the content read from the codebase before it is processed by the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:58 AM
Security Audit — agent-trust-hub — hipaa