playtest-report
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes raw playtest notes from external files.
- Ingestion points: The skill uses Read, Glob, and Grep to access files at user-defined paths.
- Boundary markers: There are no explicit markers or instructions defined to prevent the agent from following commands that might be embedded in the notes being analyzed.
- Capability inventory: The skill has permissions to Read, Glob, Grep, and Write files.
- Sanitization: No content sanitization or validation logic is present to filter out malicious instructions within the data.
Audit Metadata