game-scope-check
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an indirect prompt injection attack surface by ingesting and processing untrusted data from the local project environment during scope evaluations.\n
- Ingestion points: The skill takes feature lists as input via the
argument-hintand utilizes theRead,Glob, andGreptools to catalog features from potentially untrusted project documentation and code.\n - Boundary markers: The workflow instructions do not define clear delimiters or specific instructions for the agent to ignore potentially malicious directions embedded within the project data it catalogs.\n
- Capability inventory: The skill possesses
Writepermissions to generate assessment reports andAskUserQuestionto interact with the user, which could be misused if malicious instructions are processed from the input data.\n - Sanitization: No explicit sanitization, validation, or filtering mechanisms are described for the feature names, descriptions, or estimates extracted during the inventory phase.
Audit Metadata