Skills
skills/tonone-ai/tonone/atlas-onboard/Gen Agent Trust Hub

atlas-onboard

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Vulnerability to indirect prompt injection due to the ingestion and processing of untrusted codebase data without isolation.
  • Ingestion points: The skill reads README.md, CONTRIBUTING.md, project source files, and configuration files in Step 0, Step 1, and Step 3 to build an understanding of the project.
  • Boundary markers: The instructions do not define any delimiters or instructions to ignore embedded commands within the ingested content.
  • Capability inventory: The skill uses Write and Edit tools in Step 4 to save documentation, uses Bash in Step 3 for configuration verification, and has WebFetch and WebSearch tools available.
  • Sanitization: There are no instructions to sanitize or escape the content read from the codebase before it is interpolated into the onboarding documentation template.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 02:47 PM
Security Audit — agent-trust-hub — atlas-onboard