token-documentation
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a variety of project files (e.g., JSON, CSS, TypeScript) to generate documentation, which is a potential surface for indirect prompt injection if the source files contain malicious instructions.\n
- Ingestion points: Token source files (DTCG, JSON, CSS, JS) and the
.ds-ops-config.ymlconfiguration file.\n - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands in the source data.\n
- Capability inventory: The skill is limited to generating documentation (Markdown and JSON) and does not possess capabilities for file manipulation, system command execution, or network exfiltration.\n
- Sanitization: No data sanitization steps are specified for the processed content.
Audit Metadata