skills/de-novo/skills/herbarium/Gen Agent Trust Hub

herbarium

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project Markdown files to perform documentation consistency checks and reviews.
  • Ingestion points: The skill ingests all files matching public globs in .agents/herbarium.yml, including README.md, AGENTS.md, and documents within the docs/ and skills/ directories.
  • Boundary markers: There are no explicit delimiters or instructions for the agent to ignore potentially malicious prompts embedded in the documents it is reviewing or moving.
  • Capability inventory: The agent is empowered to write, move, rename, and review documents, and executes the de-novo skills herbarium check CLI utility.
  • Sanitization: Document content is processed without identified sanitization, filtering, or instruction-stripping before agent review.
  • [COMMAND_EXECUTION]: The skill executes the de-novo skills herbarium check command to perform linting and counting functions. This is a vendor-provided CLI tool associated with the skill's author ('de-novo') and does not involve remote code downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 08:16 AM
Security Audit — agent-trust-hub — herbarium