steelman

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user assertions to perform analysis and drive tool execution.
  • Ingestion points: The skill takes user-supplied assertions regarding design, architecture, or code behavior as input (SKILL.md).
  • Boundary markers: The skill lacks explicit boundary markers or instructions to treat user input as data only, though it instructs the agent to restate the claim (SKILL.md).
  • Capability inventory: The skill encourages the use of grep, file reading, command execution (tests/commands), and web searches based on the content of the user claim (SKILL.md).
  • Sanitization: No sanitization or validation of the user-provided assertion is mentioned before it is processed by the agent's investigation tools.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:06 AM
Security Audit — agent-trust-hub — steelman