writing-emdash-docs

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to verify documentation changes. Specifically, it runs pnpm lint:quick, pnpm --dir docs build, and git diff --check. These are standard development tools used within the context of the repository to ensure documentation quality and build integrity.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes untrusted documentation content from the repository.
  • Ingestion points: Reads files located in docs/, references/, and root directories (e.g., README.md, AGENTS.md).
  • Boundary markers: None identified; the agent is instructed to read the content directly.
  • Capability inventory: The agent has the ability to write/modify local documentation files and execute shell commands for building/linting.
  • Sanitization: None identified; the agent is instructed to follow the style guides and rules while editing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 09:52 AM
Security Audit — agent-trust-hub — writing-emdash-docs