fin-guru-compliance-review
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and validate external content, creating a vector for indirect prompt injection.
- Ingestion points: The skill processes 'externally sourced filing or issuer claim', 'financial-datasets' tool outputs, and 'WebSearch' results (SKILL.md).
- Boundary markers: There are no instructions for using delimiters or boundary markers to isolate external data from the skill's internal logic.
- Capability inventory: The skill executes a local Python CLI (
src.analysis.itc_risk_cli) which may be vulnerable to command injection if the ticker inputs are derived from untrusted external data without validation (SKILL.md). - Sanitization: No sanitization or filtering procedures are specified for the external data before it is analyzed by the agent or passed to tools.
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute a local command-line analysis tool.
- Evidence: The skill uses
uv run python -m src.analysis.itc_risk_clito perform risk assessments on financial tickers (SKILL.md).
Audit Metadata