jenkins-js-ts-acrazie
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external, untrusted repository files to generate a structured interpretation report. This creates a surface for indirect prompt injection where malicious content in repository metadata could attempt to influence the agent's output or downstream automated processes.
- Ingestion points: The skill reads
package.json(engines, scripts, packageManager), lockfiles (pnpm-lock.yaml,package-lock.json,yarn.lock,bun.lock,bun.lockb), and runtime configuration files (.nvmrc,.node-version). - Boundary markers: None. The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within the ingested files.
- Capability inventory: The skill is explicitly restricted to read-only analysis mode. It does not have file-write, network access, or command execution capabilities defined in its instructions or scripts.
- Sanitization: None. The skill does not mention any sanitization, filtering, or validation of the content read from the repository files before including it in the report.
Audit Metadata