parallel-web
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate research functionality via the Parallel Web Systems API (api.parallel.ai), a well-known service for AI-assisted search and extraction.
- [SAFE]: The skill uses the
PARALLEL_API_KEYenvironment variable for authentication, which is a standard security practice for managing secrets in AI agent skills. - [SAFE]: The implementation in
scripts/parallel_web.pyis straightforward, using official Python libraries (openai,parallel-web) to interact with APIs. It contains no dynamic code execution (eval,exec), suspicious subprocess calls, or privilege escalation attempts. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It retrieves content from untrusted external web pages and incorporates this data into the agent's context, which could potentially contain malicious instructions. Evidence Chain: 1. Ingestion points: Web data processed in
scripts/parallel_web.pythrough search, research, and extract commands. 2. Boundary markers: None explicitly enforced in the script output. 3. Capability inventory: The agent has access toRead,Write,Edit, andBashtools. 4. Sanitization: No content filtering or sanitization of retrieved web data is performed.
Audit Metadata