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-webPython 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.mdand the import statement inscripts/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, andextractcommands inscripts/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, andEdittools as defined in the skill configuration, and the research script can perform filesystem writes via the-ooutput 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