weighted-scorer
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill implements a legitimate utility for decision analysis and decision matrix generation.\n- [COMMAND_EXECUTION]: The skill utilizes a local Python script (
scripts/decision_matrix.py) to process scoring data and generate Markdown reports. This script is part of the skill package, uses only standard Python libraries, and does not perform any network or unauthorized file system operations.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (criteria and option names) to build decision matrices.\n - Ingestion points: User-provided text for candidate options and evaluation criteria in
SKILL.md.\n - Boundary markers: Absent.\n
- Capability inventory: Execution of the local script
scripts/decision_matrix.pyto generate markdown tables.\n - Sanitization: Absent.
Audit Metadata