boring-social-content

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: This skill is entirely markdown-based and does not contain any Python scripts, Node.js code, or binary files.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it reads and obeys instructions found in local markdown files.
  • Ingestion points: world-code/voice.md, world-code/climax.md, world-code/method.md, world-code/creation.md, world-code/conversation.md, and world-code/crossing.md.
  • Boundary markers: Absent; the agent is instructed to treat these files as foundational rules and apply them to all outputs.
  • Capability inventory: Text generation and copywriting for social media.
  • Sanitization: None; content is loaded directly into the context to guide the LLM's persona and logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 09:28 PM