summarize-lanes

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to perform read-only operations including listing issues, viewing pull request details, and querying the GitHub API for sub-issue data.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from GitHub issue bodies and comments to generate the lane summary.
  • Ingestion points: The skill parses the body and comments of a specified GitHub issue in detailed-summary.md to identify status markers like CHECK-IN, CANDIDATE, and HANDOFF.
  • Boundary markers: No explicit delimiters are used to wrap the ingested issue content, though the skill is restricted to a 'read-only' summary role.
  • Capability inventory: The skill is limited to GitHub CLI read commands (gh issue, gh pr, gh api) and internal agent listing tools (ListAgents).
  • Sanitization: The instructions do not specify sanitization for the content retrieved from issue comments before parsing or printing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 01:25 AM