810-regulations-eu-mifid-ii

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a potential vulnerability to indirect prompt injection due to its core function of ingesting and analyzing untrusted external data.
  • Ingestion points: Step 4 in SKILL.md instructs the agent to review Java code, configuration files, APIs, and Kafka message contracts.
  • Boundary markers: While SKILL.md and the questionnaire advise treating input as non-authoritative, there are no technical delimiters to clearly separate data from instructions.
  • Capability inventory: The agent is authorized to perform complex text analysis and generate detailed reports based on the content it reviews.
  • Sanitization: The skill mandates the redaction of secrets using [REDACTED_SECRET], which is a safety practice for data exposure but does not mitigate the risk of the agent following instructions embedded in the analyzed code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 05:44 PM
Security Audit — agent-trust-hub — 810-regulations-eu-mifid-ii