skills/harshanandak/forge/kernel/Gen Agent Trust Hub

kernel

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for managing and reading from a shared issue repository, creating a potential surface for indirect prompt injection.
  • Ingestion points: Data is ingested from the Forge issue store through various forge issue commands such as list, show, search, and recap which read titles, comments, and descriptions.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to isolate content retrieved from these external issue records.
  • Capability inventory: The skill has access to the Read tool and the Bash tool, with the latter restricted to the forge:* command namespace.
  • Sanitization: There are no explicit instructions for the agent to sanitize or validate the content retrieved from issue metadata before processing it as context for further actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:07 AM
Security Audit — agent-trust-hub — kernel