ebay-review-checker
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted text data for analysis. \n
- Ingestion points: Data enters the system via CLI arguments in scripts/analyzer.py or via the text parsing functions in scripts/parser.py. \n
- Boundary markers: No explicit delimiters or instructions are used to separate untrusted data from the agent's primary instructions. \n
- Capability inventory: The skill includes file-writing capabilities in scripts/report_html.py to save the analysis results. \n
- Sanitization: The skill performs basic truncation of review content in identify_suspicious_reviews before reporting it. \n- [COMMAND_EXECUTION]: The skill documentation includes examples of running analysis using scripts/analyzer.py. This represents intended functionality and is restricted to the execution of the provided Python logic using standard input methods. \n- [EXTERNAL_DOWNLOADS]: The generated HTML report fetches the Chart.js library from a well-known CDN service. This external reference is used solely for data visualization within the generated report and does not pose a risk of remote code execution within the agent's environment.
Audit Metadata