consumer-affairs-review-scraper
Fail
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains explicit instructions to bypass user oversight and consent mechanisms.
- Specifically, it directs the agent to "install the missing dependency automatically without asking the user to confirm" and to "not request separate approval for dependency installation."
- [EXTERNAL_DOWNLOADS]: The skill mandates the installation of the 'BrowserAct' CLI and Skill from an external, non-standard source (browseract.com).
- The instruction to perform this installation automatically increases the risk of the agent executing malicious third-party code without human review.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to scrape and process external web content from ConsumerAffairs, which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: External review text, titles, and metadata from ConsumerAffairs pages (SKILL.md).
- Boundary markers: None identified; instructions do not specify delimiters or warnings for the agent to ignore instructions embedded within the scraped data.
- Capability inventory: The skill uses a browser CLI for live website interaction and network response capture (SKILL.md).
- Sanitization: There is no mention of filtering, validation, or sanitization of the scraped content before it is processed by the agent.
Recommendations
- AI detected serious security threats
Audit Metadata