parallel-web

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the parallel-web Python package to provide URL extraction functionality. This is a third-party dependency not included in standard trusted vendor lists. \n
  • Evidence: The installation instructions in SKILL.md and the import statement in scripts/parallel_web.py (from parallel import Parallel).\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8) because it retrieves and processes content from arbitrary external websites.\n
  • Ingestion points: Untrusted data enters the agent context via the search, research, and extract commands in scripts/parallel_web.py.\n
  • Boundary markers: Absent. The skill does not implement delimiters or 'ignore' instructions to isolate external content from the agent's primary directives.\n
  • Capability inventory: The agent has access to Bash, Write, and Edit tools as defined in the skill configuration, and the research script can perform filesystem writes via the -o output flag.\n
  • Sanitization: Absent. There is no evidence of filtering or escaping logic to prevent the execution of malicious instructions found within fetched web data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 08:21 AM
Security Audit — agent-trust-hub — parallel-web