run-flow-guide

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script located at scripts/flow-guide within the skill root to perform operations like listing cases and marking verdicts.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from web browsers and server-side probes, creating a surface for potential prompt injection. 1. Ingestion points: Data is read from the product application's UI (saw field) and server-side probe results (server field). 2. Boundary markers: No delimiters or ignore-instructions are specified for the ingested content. 3. Capability inventory: The skill can execute local scripts, drive a web browser, and invoke a sub-skill (root-cause) that can modify product source code. 4. Sanitization: No sanitization, escaping, or validation of external input is implemented before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:40 AM
Security Audit — agent-trust-hub — run-flow-guide