review-management

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and analyze external app store reviews based on a user-supplied App ID. These reviews are authored by third parties and represent a surface for indirect prompt injection attacks where malicious instructions could be embedded in the review text to influence the agent's analysis or output.
  • Ingestion points: The skill fetches current reviews from external app stores (Apple App Store/Google Play) during the initial assessment.
  • Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between the user's instructions and the content of the reviews being analyzed.
  • Capability inventory: While this specific skill focuses on analysis and drafting responses, it operates within an agent environment that may possess broader capabilities like file system access or tool execution.
  • Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the retrieved review content before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:04 PM
Security Audit — agent-trust-hub — review-management