x-mastery-mentor
Fail
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: CRITICALDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill uses a
javascript_toolto dynamically parse DOM elements on external websites (X.com), posing a runtime execution risk. It also generates diagnostic reports in HTML format that include external JavaScript libraries (ECharts.js) via CDN, which could execute arbitrary code when the reports are viewed in a browser environment. - [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. Ingestion points: Scene E in
SKILL.mdscrapes user profiles and tweet history from X.com. Boundary markers: The skill lacks delimiters or warnings to ignore instructions within the scraped text. Capability inventory: The skill uses browser automation (computer-use), JavaScript execution (javascript_tool), and file writing to theuser-data/directory. Sanitization: There is no evidence of sanitization or escaping of the scraped content before it is processed by the agent. - [COMMAND_EXECUTION]: The skill utilizes platform browser automation tools (
computer-useandclaude-in-chrome) to interact with social media pages, allowing for automated data collection that could inadvertently capture authenticated session data. - [DYNAMIC_EXECUTION]: Automated security scans identified
references/research/05-ai-tech-niche.mdas a malicious file (FileRepMalware), which is a critical finding for this skill repository.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
Audit Metadata