issue-lifecycle

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [Command Execution] (SAFE): The skill executes standard commands using gh, jq, sed, and date. These operations are well-scoped to the stated purpose of updating issue statuses, comments, and bodies. All commands use typical patterns for GitHub API interaction via the CLI.
  • [Indirect Prompt Injection] (LOW): The skill ingests untrusted data by reading GitHub issue bodies and comments (gh issue view). This presents a theoretical surface for indirect prompt injection if an attacker-controlled issue contains malicious instructions.
  • Ingestion points: SKILL.md (lines 53, 155) reads issue bodies and comments.
  • Boundary markers: Absent. The skill does not explicitly instruct the agent to ignore instructions found within the fetched data.
  • Capability inventory: The skill possesses the ability to edit issues and comments, providing a mechanism for an agent to propagate injected instructions or perform unintended writes if successfully influenced.
  • Sanitization: Absent. Data is processed as raw strings for replacement operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:34 PM