price-hunter
Warn
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The script
scripts/save-price.shand the commands inSKILL.mdperform database operations by interpolating raw variables into SQL strings without sanitization or parameterization, creating a SQL injection vulnerability. Evidence: thesqlite3call inscripts/save-price.shand the/prices bestcommand template. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect injection because it ingests untrusted data from web searches and processes it using vulnerable database scripts.
- [INDIRECT_PROMPT_INJECTION]: Mandatory Evidence Chain: 1. Ingestion points: Web search results for grocery prices (referenced in
SKILL.md). 2. Boundary markers: Absent; no delimiters or warnings are used to handle untrusted search content. 3. Capability inventory: Database write access viascripts/save-price.shand read access via shell-executed SQL queries. 4. Sanitization: Absent; data is directly concatenated into shell and SQL commands.
Audit Metadata