action-audit

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is authored by a trusted vendor and performs read-only auditing tasks using well-known services (GitHub CLI and API). It explicitly forbids mutating operations through rules and platform configuration.
  • [COMMAND_EXECUTION]: The skill instructs the agent to construct shell commands using variables derived from user input and parsed file content. While this creates a potential command injection surface if the agent does not sanitize inputs, it is a functional requirement for the auditing task.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks. 1. Ingestion points: Step 3 parses 'uses:' references from external GitHub workflow files. 2. Boundary markers: Absent; the skill does not define delimiters for parsed data. 3. Capability inventory: The skill uses the Bash tool to execute 'gh' commands and the GitHub API. 4. Sanitization: Absent; there are no instructions to sanitize or validate strings extracted from workflow files before they are used in subsequent API calls in Step 4.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 02:16 PM