gsp-audit-scorecard
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes game audit findings, which acts as a vector for untrusted data ingestion. If the audit findings are sourced from untrusted external content, they could contain malicious instructions designed to influence the agent's behavior during the scorecard generation process.
- Ingestion points: Audit findings processed in the session to generate scorecards (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the input data as non-executable text.
- Capability inventory: The skill has the capability to write structured output to
docs/game-studio/audit/scorecard.jsonanddocs/game-studio/audit/audit-summary.md(SKILL.md). - Sanitization: There are no instructions for sanitizing or validating the content of the findings before writing them to the filesystem.
Audit Metadata