rhdh-plugin-wiring
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze untrusted data from a local plugin repository (source code, package metadata, and manifests) to generate configuration files. This creates a surface where malicious content embedded in those files could attempt to influence the agent's output or behavior.
- Ingestion points: Files including
package.json,src/plugin.ts,src/plugin.tsx,src/index.ts, anddist-dynamic/dist-scalprum/plugin-manifest.jsonare read into the agent context. - Boundary markers: Absent. There are no instructions to use specific delimiters or to disregard natural language instructions found within the analyzed files.
- Capability inventory: The agent performing this skill possesses file system read capabilities and is instructed to generate complex YAML output based on the findings.
- Sanitization: Absent. The skill does not provide instructions for escaping, validating, or filtering the content extracted from the plugin source files before interpolation into the generated configuration.
Audit Metadata