senior-jsts
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze JavaScript and TypeScript artifacts, which may contain adversarial instructions designed to influence the agent's behavior during a code review.
- Ingestion points: The skill explicitly instructs the agent to read and trace repository code, packages, lockfiles, and schemas in SKILL.md.
- Boundary markers: While the skill uses clear instructional sections like 'Establish the actual task' and 'Run a cheap concern scan' to guide the agent, it does not employ specific character-based delimiters (like triple backticks or custom tags) for the code it analyzes.
- Capability inventory: The skill itself contains no executable code, scripts, file system write operations, or network capabilities.
- Sanitization: The skill contains detailed defensive instructions in references/security-and-trust.md for the agent to identify and report missing input sanitization, dangerous sinks (like innerHTML or eval), and unauthorized data flow in the code it is reviewing, which serves to focus the agent on security verification.
Audit Metadata