slide-deck

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest content from external documents, notes, and brand guidelines to generate slide decks, which creates an attack surface for indirect prompt injection.
  • Ingestion points: Reads local files in the working directory such as BRAND.md, brand-guidelines.md, and user-provided source documents or transcripts (SKILL.md).
  • Boundary markers: Absent. The instructions do not specify any delimiters or directives to the agent to treat ingested file content as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill performs file system write operations to save the generated presentation as an HTML file (SKILL.md).
  • Sanitization: Absent. The instructions do not provide requirements for escaping or sanitizing data extracted from source documents before it is embedded into the final HTML/JS file, which could theoretically allow for the injection of malicious scripts if the source material is untrusted.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 08:20 PM
Security Audit — agent-trust-hub — slide-deck