game-playtest
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from playtest sessions which could contain malicious instructions designed to override agent behavior.
- Ingestion points: The workflow ingests external data through 'Timestamped Observations' and 'Post-Session Survey Responses' as outlined in the templates in SKILL.md.
- Boundary markers: The skill does not define clear boundary markers or instructions to ignore embedded commands when processing player-provided text.
- Capability inventory: The agent uses allowed tools such as Read and Write to analyze these inputs and generate markdown reports, creating a path for potential unauthorized file operations if instructions are followed.
- Sanitization: There is no mention of input validation or sanitization of the playtest data before it is analyzed by the agent.
Audit Metadata