pp-chrome-history
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to download and install a CLI tool from the
@mvanhorn/printing-press-libraryNPM package or from the author's GitHub repository. These sources are controlled by the skill's author. - [REMOTE_CODE_EXECUTION]: The installation process for the required
chrome-history-pp-cliinvolves fetching and executing remote code vianpxorgo installat runtime. - [COMMAND_EXECUTION]: The skill functions by running the
chrome-history-pp-clibinary with various commands to read from the Chrome History database, including support for raw SQL queries. - [PROMPT_INJECTION]: The skill processes untrusted web titles and URLs, which constitutes an indirect prompt injection surface where malicious web content could influence the agent's instructions.
- Ingestion points: Data is ingested from the local Chrome History SQLite database via commands like
searchandjourneys(SKILL.md). - Boundary markers: The instructions lack explicit delimiters or safety prompts to isolate data from the agent's command logic.
- Capability inventory: The skill can execute local commands, read sensitive browser files, and write to a local cache directory (SKILL.md).
- Sanitization: The skill does not specify any sanitization or validation of the page titles or URLs before they are passed to the agent context.
Audit Metadata