view-audit-report

Warn

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The shell commands defined in the procedure interpolate user-supplied machine names and timestamps. This pattern is susceptible to command injection and directory traversal if the agent executes these strings without proper sanitization of the placeholders.
  • [PROMPT_INJECTION]: The skill reads and displays the content of external audit reports, creating a surface for indirect prompt injection where malicious instructions could be embedded in the reports. (1) Ingestion points: Reading audit-report.md in SKILL.md. (2) Boundary markers: None. (3) Capability inventory: Subprocess calls using shell commands (ls, head). (4) Sanitization: None.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 05:15 PM
Security Audit — agent-trust-hub — view-audit-report