stitch::upload-to-stitch

Fail

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill instructions direct the agent to harvest API keys from sensitive configuration files belonging to other applications, specifically ~/.claude.json, ~/.gemini/settings.json, and .gemini/antigravity/mcp_config.json.
  • [CREDENTIALS_UNSAFE]: Sensitive API keys are passed as plain-text command-line arguments to the upload_to_stitch.py script via the --api-key flag, which exposes them in system process lists.
  • [DATA_EXFILTRATION]: The skill reads local files (images, HTML, Markdown) and transmits their contents to an external API (stitch.googleapis.com).
  • [COMMAND_EXECUTION]: The skill utilizes the run_command (Bash) tool to execute a Python script that performs network operations and file reading.
  • [PROMPT_INJECTION]: The skill instructions include explicit 'IMPORTANT' markers that command the agent to bypass standard tool calls in favor of the provided script, potentially overriding default safety behaviors for data handling.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local files for upload without explicit sanitization or boundary markers between the data and the execution logic.
  • Ingestion points: Local files specified by the --file-path argument in upload_to_stitch.py.
  • Boundary markers: Absent; there are no delimiters or instructions to ignore embedded content within the files being read.
  • Capability inventory: File reading via Python's open(), network transmission via urllib.request.urlopen, and shell execution via run_command.
  • Sanitization: Absent; the script performs a direct base64 encoding and transmission of the raw file content.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 31, 2026, 04:14 AM
Security Audit — agent-trust-hub — stitch::upload-to-stitch