scout

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes the full conversation context to provide recommendations, creating an attack surface where malicious instructions embedded in the conversation could influence the agent's behavior.
  • Ingestion points: According to SKILL.md, the agent is instructed to "Review the conversation" and "Read the conversation" to understand the user's goal.
  • Boundary markers: The instructions do not define any delimiters or specific warnings to ignore instructions found within the processed conversation history.
  • Capability inventory: The skill has access to file system tools (Read, Glob, Grep) and network tools (WebFetch, WebSearch), which could be misused if the agent is manipulated by injected data.
  • Sanitization: There are no instructions for sanitizing or validating the content extracted from the conversation context before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — scout