app-rejection-recovery

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data by instructing the agent to ask users for their full, verbatim app rejection messages. This creates a potential surface for indirect prompt injection if a rejection message were to contain malicious instructions intended to manipulate the agent's output.
  • Ingestion points: The skill instructs the agent in SKILL.md to "Ask the user to paste the full rejection message verbatim — including the guideline number(s)".
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided to separate the user-provided rejection content from the agent's internal logic.
  • Capability inventory: The skill does not possess capabilities for network operations, file system writes, or subprocess execution, significantly limiting the impact of any potential injection.
  • Sanitization: There is no explicit sanitization or validation logic defined for the external text input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 12:51 PM
Security Audit — agent-trust-hub — app-rejection-recovery