topic-finder

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's instructions were evaluated for behavior override or safety bypass attempts. The instructions explicitly prioritize data accuracy and verification, and no malicious injection patterns were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes external, untrusted data to generate content topics.
  • Ingestion points: The skill ingests user-provided materials such as news articles, interview transcripts, and book excerpts as defined in 'SKILL.md'.
  • Boundary markers: The skill does not define explicit delimiters or 'ignore embedded instructions' markers when interpolating user-provided materials into the agent's context.
  • Capability inventory: The agent has the capability to write to the local file system (e.g., creating and saving topic cards) as specified in 'SKILL.md' and 'references/輸出模板.md'.
  • Sanitization: No explicit sanitization, filtering, or validation of the content within the ingested external materials is described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 07:03 PM
Security Audit — agent-trust-hub — topic-finder