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