kelly-content
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a startup script (
app/start.sh) that executes shell commands to install Node.js dependencies and launch a local web server usingnode app/server/launcher.ts. This behavior is central to the skill's intended functionality of providing a local review application. - [EXTERNAL_DOWNLOADS]: The skill's installation process fetches required libraries from the official NPM registry, a well-known and trusted service for Node.js development.
- [PROMPT_INJECTION]: The skill processes untrusted user-provided source material to generate content drafts, which introduces a potential surface for indirect prompt injection. Malicious instructions within the source text could attempt to influence the agent's content generation or subsequent tasks.
- Ingestion points: The
scripts/generate_batch.tsscript reads source content from files or text input. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are used during the data processing phase.
- Capability inventory: The skill possesses capabilities to write files to the local filesystem and host a local web server.
- Sanitization: The skill does not explicitly sanitize the source content for potential adversarial instructions before processing it.
Audit Metadata