assess-pci

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the $ARGUMENTS parameter.
  • Ingestion points: User input provided in $ARGUMENTS is directly interpolated into the prompt used to spawn the security-auditor agent in SKILL.md.
  • Boundary markers: There are no boundary markers or delimiters around the $ARGUMENTS variable to distinguish user input from the agent's core instructions.
  • Capability inventory: The skill utilizes the Task and Skill tools to perform complex security audits and generate compliance reports.
  • Sanitization: The skill lacks sanitization or validation logic to filter out potentially malicious instructions within the user-provided scope description.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:21 AM