dsh-plugin-lint
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill audits external, potentially untrusted DSH plugin repositories, which could contain malicious instructions designed to influence the agent's assessment of the plugin's safety or quality.
- Ingestion points: The agent and the provided
scripts/lint.mjsscript readpackage.json,cordis.patch.yml, and compiled build artifacts (such asclient.js) from the target plugin directory. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when the agent reads the content of the target plugin files.
- Capability inventory: The skill executes a local Node.js script (
scripts/lint.mjs), performs arbitrary filesystem reads within the target directory, and utilizes browser automation viaego-browserto perform DOM assertions. - Sanitization: The skill does not perform explicit sanitization or content validation of the plugin files before they are processed by the agent's logic for quality review.
Audit Metadata