skills/logicober/worldview-skills/worldview-game-asymmetric-information-cooperation/Gen Agent Trust Hub
worldview-game-asymmetric-information-cooperation
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided game fiction, role definitions, and interaction descriptions to generate comprehensive game design documents (e.g.,
mechanic.md,tunables.yaml) and potentially implement runtime code for cooperative loops. It does not provide explicit instructions or mechanisms to sanitize or delimit this user-provided content, which could allow malicious inputs to influence the generated logic or documentation. - Ingestion points:
SKILL.md(What the user gives section) andtemplates/mechanic-contract.mdprocess user-defined roles, locations, tools, senses, and communication fiction. - Boundary markers: The skill does not define specific delimiters or instructions (e.g., 'ignore previous instructions') to guard against malicious commands embedded within user-supplied strings.
- Capability inventory: The skill produces multiple markdown and YAML files and is capable of generating runtime game loops within the agent's environment as described in the 'What the user receives' section of
SKILL.md. - Sanitization: There is no evidence of escaping, validation, or filtering of user-provided content before it is interpolated into the final deliverables.
Audit Metadata