research-company
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the 'reportlab' library from the Python Package Index (PyPI). This is a well-known and legitimate library used for programmatically creating PDF documents.
- [COMMAND_EXECUTION]: The skill uses shell commands to install dependencies and execute a local Python script ('scripts/generate_report.py') to process researched data. These actions are aligned with the skill's primary function of report generation.
- [PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection due to the ingestion of data from external company websites. 1. Ingestion points: Phase 1 of 'SKILL.md' involves performing web fetches and searches on external URLs. 2. Boundary markers: The skill does not define specific delimiters or instructions to help the agent distinguish between its system instructions and the data fetched from external sources. 3. Capability inventory: 'SKILL.md' (Phase 3) executes shell commands for file management and script execution. 4. Sanitization: While the generation script parses data using standard JSON methods, no specific sanitization is performed on the gathered text to filter out potential embedded instructions.
Audit Metadata