result-integrator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and process text data ('情节点分析结果') from multiple external sources. This creates a surface where malicious instructions could be embedded in the data being analyzed.
  • Ingestion points: Defined in SKILL.md under the '输入要求' (Input Requirements) section.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions to separate untrusted data from the agent's core logic.
  • Capability inventory: The skill is granted the Read tool permission in SKILL.md.
  • Sanitization: No sanitization or validation logic is present to filter out potential commands from the input data.
  • External Source Access (SAFE): The skill references local files within its own directory structure ({baseDir}/references/examples.md) and does not perform network requests to untrusted or non-whitelisted domains.
  • Command Execution (SAFE): No dangerous shell commands, system modifications, or persistence mechanisms were detected in the instructions or examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:14 PM