NYC

pptx-presentation-builder

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (SAFE): No direct injection attempts or instructions to bypass safety guidelines were found within the skill's instructions.\n- [DATA_EXFILTRATION] (SAFE): No sensitive file access patterns or unauthorized network communication mechanisms were detected.\n- [REMOTE_CODE_EXECUTION] (SAFE): No external dependencies, package installations, or remote script download patterns are present.\n- [INDIRECT_PROMPT_INJECTION] (LOW): A vulnerability surface exists due to the ingestion and processing of untrusted user data to generate presentation content.\n
  • Ingestion points: User-provided deck briefs and slide metadata defined in the prompt examples.\n
  • Boundary markers: The skill uses Markdown headers and code blocks (YAML/Markdown) for structure, but it lacks explicit instructions to the agent to disregard instructions nested within the user's data.\n
  • Capability inventory: The skill utilizes 'Write', 'Read', and 'Task' tools to generate '.pptx' and '.pdf' files on the local system.\n
  • Sanitization: There is no evidence of sanitization or validation of user-provided strings before they are interpolated into slide templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:51 PM