deal-with-security-advisory

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gh (GitHub CLI) and git tools to automate security advisory management. Actions include fetching advisory JSON, creating private forks, and creating GitHub releases on the vendor's repository.- [PROMPT_INJECTION]: The skill ingests untrusted data from security researchers via GitHub Security Advisory descriptions and notes. This data is processed by the agent to understand the vulnerability, creating an indirect prompt injection surface.
  • Ingestion points: Content retrieved from the GitHub API in Step 0 (gh api ... security-advisories/{{ghsaId}}).
  • Boundary markers: The skill does not define specific delimiters for separating researcher-provided text from internal instructions.
  • Capability inventory: The agent has the ability to execute shell commands via gh and git.
  • Sanitization: No specific sanitization or filtering of the advisory content is performed before the agent reads it.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 09:14 PM