china-pptx-author

Warn

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is configured to execute a local Python script scripts/generate_a_share_ppt.py via a shell command string.
  • [COMMAND_EXECUTION]: Potential for command injection vulnerability. User-controlled variables including {{COMPANY_NAME}}, {{TICKER}}, and {{INDUSTRY_NAME}} are interpolated directly into a shell command template. A malicious user could provide input containing shell metacharacters (e.g., ;, &&, or |) to execute unauthorized commands on the host environment.
  • [PROMPT_INJECTION]: Vulnerability to indirect prompt injection through external data sources.
  • Ingestion points: The skill fetches dynamic content from external financial data tools (iFind MCP and AkShare MCP), including company descriptions and industry analysis (SKILL.md).
  • Boundary markers: No delimiters or instructions are used to signal the agent to ignore potentially malicious instructions embedded within the fetched financial data.
  • Capability inventory: The skill has the ability to execute local scripts and write files to the local file system (SKILL.md).
  • Sanitization: There is no evidence of sanitization or escaping of the external data before it is processed and included in the presentation output.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 13, 2026, 01:06 PM
Security Audit — agent-trust-hub — china-pptx-author