parallel-research

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill defines a workflow for ingesting and processing untrusted data from external websites, creating a surface where malicious instructions could be embedded in research results. -- Ingestion points: External content is pulled into the agent's context through the WebFetch and WebSearch tools during the execution phase. -- Boundary markers: Absent. The prompt templates provided in the skill do not include explicit delimiters or instructions to ignore embedded commands within the fetched data. -- Capability inventory: The skill grants access to file system tools (Read, Grep, Glob) and complex orchestration capabilities (Task). -- Sanitization: Absent. There is no requirement or instruction for validating or filtering external content before it is integrated into the synthesis.
  • [NO_CODE]: The skill consists entirely of Markdown instructions and metadata. It does not contain any executable code, shell scripts, or package manifests.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 04:51 AM