skills/tonone-ai/tonone/keel-vendor/Gen Agent Trust Hub

keel-vendor

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements standard vendor management procedures including auditing local documentation and applying scorecard frameworks. Its operations are consistent with its stated purpose.
  • [COMMAND_EXECUTION]: Employs basic shell commands (find and grep) to locate vendor-related files within the project repository. These commands are used for discovery and do not involve privileged execution or external data piping.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its ingestion of untrusted data from local files.
  • Ingestion points: Reads content from .md, .csv, and .json files found in the local environment during the Step 1 audit.
  • Boundary markers: None; file content is analyzed directly without clear delimiters to isolate potential instructions within the data.
  • Capability inventory: Includes the ability to execute shell commands (Bash) and access external websites (WebFetch, WebSearch).
  • Sanitization: No content sanitization or validation logic is specified for the data read from project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:57 AM
Security Audit — agent-trust-hub — keel-vendor