build-deliverable-deck

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Vulnerability to indirect prompt injection via ingestion of untrusted engagement artifacts.
  • Ingestion points: The skill reads markdown files from engagements/<customer>/discovery/ and engagements/<customer>/assessments/ (SKILL.md) to build the presentation content.
  • Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the processed artifacts.
  • Capability inventory: The skill can write files to the local file system and invoke downstream skills such as red-hat-quick-deck and pptx.
  • Sanitization: No sanitization or validation is applied to the content extracted from external reports before it is used to generate the final deliverable.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:30 PM
Security Audit — agent-trust-hub — build-deliverable-deck