practice

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of external data from the project environment.
  • Ingestion points: Untrusted data enters the agent context through the $ARGUMENTS variable and by reading project-specific template overrides from the ${CLAUDE_PROJECT_DIR} directory.
  • Boundary markers: The instructions lack explicit delimiting markers or system instructions to ignore potentially malicious embedded content within the ingested files or user arguments.
  • Capability inventory: The skill possesses capabilities to write files to the local filesystem at the songwriting/practice/ path.
  • Sanitization: There are no documented procedures for sanitizing, validating, or escaping external content before it is interpolated into the prompts for agent execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 07:55 PM
Security Audit — agent-trust-hub — practice