error-handling
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code and scripts ("Review scripts, client components, bundles, or runtime behavior"). This creates an attack surface where an adversary could embed malicious instructions within the code files being reviewed to manipulate the agent's output or behavior.
- Ingestion points: The agent reviews external JavaScript files and browser execution paths as specified in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or "ignore" instructions to separate the untrusted code from the agent's core instructions.
- Capability inventory: The skill focus is on analysis and reporting; it does not explicitly define file-write or network operations, though the agent's host environment may provide them.
- Sanitization: No explicit sanitization or filtering of the code content is mentioned in the instructions.
Audit Metadata