yy-wechat-to-markdown
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Node.js script (
scripts/src/cli.ts) to perform article conversion. This script includes the capability to write output to the local filesystem usingfs.writeFileSyncbased on user-provided arguments. - [EXTERNAL_DOWNLOADS]: The skill performs network requests to
mp.weixin.qq.comto fetch the HTML content of WeChat articles. This behavior is necessary for its stated purpose but involves downloading data from the public internet. - [PROMPT_INJECTION]: The skill processes untrusted HTML data from an external website, creating a surface for indirect prompt injection.
- Ingestion points: External article content is fetched in
scripts/src/cli.ts. - Boundary markers: Absent. The skill does not use delimiters or instructions to the agent to ignore embedded commands in the converted text.
- Capability inventory: The skill has script execution and filesystem write permissions (
scripts/src/cli.ts). - Sanitization: The skill converts HTML to Markdown via regex in
scripts/src/parser/html-to-md.ts, which strips tags but does not sanitize the text for potentially malicious instructions.
Audit Metadata