planning-create-pitch-deck

Warn

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits extreme 'context stuffing' across multiple reference files, including references/architecture-patterns.md, references/code-organization.md, references/deployment-pipelines.md, references/error-handling.md, references/performance-optimization.md, references/security-best-practices.md, references/state-management.md, and references/testing-strategies.md.
  • Each of these files contains 150 sections of identical, irrelevant technical boilerplate text regarding kernel space interactions, system calls (epoll_wait, io_uring), and CPU cache locality.
  • This repetitive content is unrelated to the skill's stated purpose (investor pitch deck creation) and appears designed to bloat the agent's context window with junk data. This can bias model behavior, increase latency, and cause the agent to lose track of the actual user goals or safety constraints.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 4, 2026, 05:20 AM
Security Audit — agent-trust-hub — planning-create-pitch-deck