training-path
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by processing untrusted external data. Ingestion points: The agent reads codebase manifests, data models, and learner profiles from the environment (SKILL.md). Boundary markers: No explicit delimiters or boundary markers are defined to isolate processed content from system instructions. Capability inventory: The skill has permission to read the filesystem and write analysis reports to the local directory (SKILL.md). Sanitization: The instructions include a manual safety check requiring the agent to exclude personally identifiable information (PII) from its output.
- [COMMAND_EXECUTION]: The skill performs local file system operations to read the project codebase for its analysis phases. It writes findings to the docs/ folder and appends execution metadata to the platform-specific project directory in ~/.claude/projects/.
Audit Metadata