pp-toodledo
Warn
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the toodledo-pp-cli tool from the vendor's official repositories on GitHub and NPM.
- [REMOTE_CODE_EXECUTION]: Installs the CLI tool using standard go install and npx commands from the vendor's modules.
- [COMMAND_EXECUTION]: Uses the Bash tool to execute the toodledo-pp-cli binary for all Toodledo management tasks.
- [DATA_EXFILTRATION]: The skill provides features enabling data transmission to external locations. The --deliver webhook: flag allows command output, including task data and account info, to be POSTed to arbitrary URLs. The feedback command also supports remote transmission if configured with a feedback endpoint.
- [PROMPT_INJECTION]: Features an indirect prompt injection surface by ingesting data from the Toodledo API and local files. 1. Ingestion points: Data is ingested via task listing, reviews, and file-based capture. 2. Boundary markers: The instructions lack markers to prevent the agent from obeying instructions embedded in task content. 3. Capability inventory: The skill has shell access, file writing capabilities, and network exfiltration sinks. 4. Sanitization: No sanitization of external content is specified before processing.
Audit Metadata