intelligems-rollout-brief

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill ingests untrusted data (test details, overview analytics, and segment analysis) from an external API in Step 4.
  • Ingestion points: rollout.py fetches test metadata and segment data via API calls.
  • Boundary markers: None. The instructions do not specify any delimiters or safety prompts to prevent the agent from obeying instructions embedded in the test data.
  • Capability inventory: The agent can execute shell commands (python3, cp), write files, and perform network requests (API + Slack).
  • Sanitization: No sanitization is mentioned for the external content before it is processed into 'Executive Summaries' or 'Recommendations'.
  • Command Execution (HIGH): Step 2 and Step 4 involve copying (cp) and executing (python3) a script named rollout.py. This script is sourced from a references/ directory not provided for analysis, representing unverified code execution.
  • Data Exfiltration (MEDIUM): Step 6 explicitly supports sending analysis results to a user-provided Slack webhook URL (--slack "<webhook_url>"). An attacker could exploit this by providing a malicious webhook URL to exfiltrate sensitive financial impact or segment data analyzed by the skill.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 05:17 AM