product-reviews-ratings
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides logic for a review submission system that ingests untrusted user-generated content, creating a potential vector for indirect prompt injection.
- Ingestion points: The
submitReviewfunction inSKILL.mdprocesses reviewtitleandbodyfromreq.bodywithout specialized sanitization for AI context. - Boundary markers: There are no boundary markers or explicit instructions to downstream AI components to ignore instructions embedded within the review text.
- Capability inventory: The skill allows review creation in the database, Bayesian rating calculations, and generation of schema.org JSON-LD markup which could be used to propagate malicious content to search engines or internal agents.
- Sanitization: While the code snippet mentions spam and profanity checks (
checkSpam,checkProfanity), these do not mitigate adversarial prompt injection or script injection that might affect automated analysis tools.
Audit Metadata