playtest-report
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's 'analyze' mode ingests raw playtest notes from user-provided file paths, which creates a potential surface for indirect prompt injection. Maliciously crafted notes could attempt to influence the agent's behavior during the analysis phase.
- Ingestion points: Raw notes are read from a file path in Phase 2B.
- Boundary markers: The instructions do not define specific delimiters to separate the raw input from the agent's internal logic.
- Capability inventory: The skill allows writing reports to the local file system and spawning sub-tasks for a creative director review.
- Sanitization: No explicit sanitization or filtering of the input notes is mentioned before the analysis process.
Audit Metadata