worldview-game-restore-power-under-pressure
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied project files, maps, and system configurations, which are external and untrusted data sources. These ingestion points could be exploited via indirect prompt injection to influence the agent's behavior during design or implementation phases.
- Ingestion points:
SKILL.md('What the user gives' section) andREADME.md('The Agent recovers the missing implementation facts'). - Boundary markers: The instructions do not define delimiters or specific 'ignore instructions' warnings for external content.
- Capability inventory: The skill allows the agent to modify project source code, use local engine tooling, and perform automated testing.
- Sanitization: There are no explicit requirements for sanitizing or validating the contents of the ingested files.
Audit Metadata