aa-segment-performance-comparator

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the open command to launch a locally generated HTML report from the /tmp directory. This is consistent with the skill's primary purpose of providing visual analytics to the user.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting data from Adobe Analytics and interpolating it into an HTML template.
  • Ingestion points: External data is retrieved via the runReport, findSegments, and findMetrics Adobe Analytics tools.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data interpolated into the HTML.
  • Capability inventory: The skill possesses shell execution capabilities through the open command used in the final phase.
  • Sanitization: There is no explicit requirement in the instructions to sanitize or escape data (such as segment names or metric values) before it is populated into the {PLACEHOLDER} tokens in the HTML template.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 11:50 PM
Security Audit — agent-trust-hub — aa-segment-performance-comparator