presentation-architect

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest high-level ideas or briefs from users to generate exhaustive presentation scripts. It lacks explicit boundary markers or instructions for the agent to treat the input as untrusted data, creating a potential surface for indirect prompt injection if a brief contains malicious instructions designed to hijack the agent's behavior.
  • Ingestion points: User-provided presentation briefs and requests (SKILL.md, Workflow section).
  • Boundary markers: Absent; the skill does not specify the use of delimiters or 'ignore instructions within data' guards when interpolating user content.
  • Capability inventory: The skill instructs the agent to generate and save output as a Markdown (.md) file.
  • Sanitization: Absent; there is no mention of filtering or validating the user brief content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 09:11 PM