xkcd

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's setup process in runtime/scripts/dependencies.mjs performs an automated installation of Node.js dependencies from the npm registry using npm ci. It also downloads the Chromium browser via Playwright when browser-based features are first used.
  • [COMMAND_EXECUTION]: The skill relies on system binaries to perform its core functions, executing git to retrieve source code, gh (GitHub CLI) to interact with pull requests, and node to run its internal management scripts.
  • [DATA_EXFILTRATION]: The skill transmits technical summaries and generated comic content to GitHub as PR comments using the gh api. To mitigate the risk of leaking sensitive information, the redact utility in runtime/scripts/core.mjs identifies and masks patterns matching API keys, tokens, and private keys. It also explicitly excludes .env files from code capture.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes source code from potentially untrusted external repositories. While it instructs the agent to treat code as data and includes a redaction layer, it remains exposed to indirect prompt injection if malicious instructions are hidden within the analyzed code.
  • Ingestion points: Source code is ingested through captureLocal and capturePr in runtime/scripts/core.mjs.
  • Boundary markers: runtime/guide.md explicitly directs the agent to treat code as data, not instructions.
  • Capability inventory: The skill can execute shell commands (git, gh, npm), perform file system operations, and interact with the GitHub API.
  • Sanitization: The redact function in runtime/scripts/core.mjs provides automated filtering of hardcoded credentials before they are processed or exported.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 03:01 AM