Skills
Navigate
skills/halcyon666/write-skills/write-to-docusaurus/Gen Agent Trust Hub

write-to-docusaurus

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to run local shell commands like pnpm build and pnpm start to validate documentation projects. This provides a vector for arbitrary code execution defined within the target project's build scripts.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection when processing external articles or news analysis. Ingestion points: Article content and external summaries (Step 3.6). Boundary markers: None; the skill lacks delimiters to isolate external text. Capability inventory: File-write operations and shell command execution. Sanitization: Limited to MDX syntax escaping for compilation safety.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 03:55 PM
Security Audit — agent-trust-hub — write-to-docusaurus