specialist-engineering-security-engineer

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data by interpolating the {the user's question} variable directly into the specialist agent's prompt, creating a potential surface for instructions within the data to influence agent behavior.
  • Ingestion points: User input is ingested via the {the user's question} variable in the SKILL.md file.
  • Boundary markers: The skill lacks explicit boundary markers (such as XML tags or specific delimiters) or instructions to ignore embedded commands around the user input variable.
  • Capability inventory: The specialist agent is granted a broad persona and access to security assessment reasoning, which could be redirected by malicious user input.
  • Sanitization: No sanitization, escaping, or validation is performed on the user's question before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-engineering-security-engineer