browser-extension-builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No instructions to override behavior or bypass safety filters were detected.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials (API keys, tokens) or sensitive file paths were found. Use of
chrome.storageis limited to standard extension data persistence. - Obfuscation (SAFE): No Base64, zero-width characters, homoglyphs, or other encoding techniques were used to hide content.
- Unverifiable Dependencies & Remote Code (SAFE): The skill does not include package managers (npm/pip) or remote script execution (curl/wget).
- Privilege Escalation (SAFE): No commands for escalating system privileges (sudo/chmod) or OS-level modifications were found.
- Persistence Mechanisms (SAFE): The skill does not attempt to modify startup files, shell profiles, or system registries.
- Metadata Poisoning (SAFE): Metadata is descriptive and aligns with the extension-building purpose.
- Indirect Prompt Injection (SAFE): While the skill demonstrates data ingestion from web pages, it is provided as a development template.
- Ingestion points: content.js (via document.querySelector).
- Boundary markers: None.
- Capability inventory: DOM manipulation, chrome.storage access.
- Sanitization: None present in basic template code.
- Dynamic Execution (SAFE): No use of eval(), exec(), or runtime compilation was detected.
Audit Metadata