corporate_spy

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill processes external PDF files from corporate announcements, which could contain instructions intended to manipulate the agent's summarization or behavior. Ingestion points: PDF filings downloaded from NSE/BSE exchange websites. Boundary markers: None specified in documentation. Capability inventory: Network requests (scraping/downloading) and text summarization. Sanitization: No content validation or sanitization described.
  • [NO_CODE] (SAFE): No executable scripts or implementation code were provided for analysis. The evaluation is based solely on the description in the SKILL.md file.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 10:54 PM