woostack-visualize
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple sources which could contain malicious instructions.\n
- Ingestion points: Pasted proposals, local working-copy files, and remote GitHub resources (PRs, issues, blobs) specified in SKILL.md.\n
- Boundary markers: Includes explicit instructions to treat all supplied and remote text as untrusted evidence, never instructions.\n
- Capability inventory: Uses the gh tool for remote resource access, reads local files, and writes HTML output to the filesystem as described in SKILL.md.\n
- Sanitization: Mandates safe encoding of all inserted text and strictly forbids the reproduction of executable source HTML.\n- [COMMAND_EXECUTION]: The skill utilizes the gh (GitHub CLI) tool to resolve and read remote repository artifacts. This is a standard capability for GitHub integration and is used in a read-only capacity.\n- [DYNAMIC_EXECUTION]: The skill generates bespoke HTML files that may include inline JavaScript for interaction. The instructions mitigate risk by requiring the output to be self-contained, offline, and safe-encoded to prevent the source content from directing tool usage or browser consent.
Audit Metadata