fstack-counselors

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to gather user-provided questions and context files into a brief that is then passed to multiple independent models. \n
  • Ingestion points: User prompts and external context files (as specified in SKILL.md). \n
  • Boundary markers: Absent. The instructions do not specify using delimiters or warnings to ignore potential instructions within the user-provided data. \n
  • Capability inventory: The skill uses the agent's ability to spawn sub-tasks or query multiple models; no internal scripts or network operations are included. \n
  • Sanitization: Absent. Content from files and user input is included in the brief without validation or filtering. \n- [COMMAND_EXECUTION]: The documentation references an external third-party CLI tool (counselors) and its GitHub repository as a recommended way to perform the coordination. While the skill does not automatically install or execute the tool, it suggests its use if available in the environment, which relies on a tool not explicitly verified as a trusted vendor resource.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 08:59 AM
Security Audit — agent-trust-hub — fstack-counselors