workflow-performance

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted user input to drive an automated multi-step workflow.
  • Ingestion points: The user's prompt is used directly as context for the performance workflow (SKILL.md).
  • Boundary markers: No delimiters or explicit instructions are provided to the agent to treat user input as data rather than instructions.
  • Capability inventory: The workflow triggers several high-capability actions including /investigate, /plan, and /code which involve file system interaction and code modification.
  • Sanitization: The skill does not implement any validation or sanitization of the input context to prevent the execution of instructions embedded within the user prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 07:40 AM
Security Audit — agent-trust-hub — workflow-performance