readme-updater

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes metadata and prose from COMPANY.md files to generate entries in the root README.md, creating a surface for indirect prompt injection.
  • Ingestion points: Workflow step 2 involves reading name, description, and upstream source data from COMPANY.md files in various directories.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to help the agent distinguish the processed data from its internal instructions.
  • Capability inventory: The skill is capable of executing a local script (~/paperclip scripts/generate-company-assets.ts) and performing filesystem writes to README.md.
  • Sanitization: There is no mention of sanitizing or validating the extracted data before it is interpolated into the README or used as context for other operations.
  • [COMMAND_EXECUTION]: The skill executes a local script at ~/paperclip scripts/generate-company-assets.ts to generate organizational charts. This command uses project-specific tooling belonging to the author, paperclipai.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 03:35 PM