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

gates

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands via the Bash tool to interact with the forge CLI. These commands modify the .forge/config.yaml file to enable or disable workflow gates and record approval events. This access is consistent with the skill's stated purpose of managing project enforcement rails.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided input for <gate-id> and <issue-id>, which are directly interpolated into Bash commands.
  • Ingestion points: User input for gate and issue identifiers in SKILL.md (e.g., forge gate disable <gate-id>).
  • Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from interpreting content within these identifiers as shell commands.
  • Capability inventory: The skill has access to Bash, Read, Grep, and Glob tools, providing significant local execution and file system access.
  • Sanitization: There is no mention of input validation or escaping for the user-supplied identifiers before they are passed to the terminal.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:07 AM
Security Audit — agent-trust-hub — gates