llms-txt-generator
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from live websites during its crawling phase, creating a vulnerability surface where a malicious site could attempt to inject instructions.
- Ingestion points: External website content retrieved during the crawl defined in
SKILL.md(Step 3B). - Boundary markers: Absent; there are no explicit delimiters or instructions to treat the crawled content as untrusted data.
- Capability inventory: The skill is authorized to write files to the local filesystem and initiate GitHub Pull Requests as seen in
SKILL.md(Step 7 and 8). - Sanitization: Absent; no specific sanitization or filtering of the crawled content is performed before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill instructions advise the use of
npxto run the installation CLI and the Chrome DevTools MCP server. - [EXTERNAL_DOWNLOADS]: The skill relies on external packages downloaded from the NPM registry for its core functionality and installation.
Audit Metadata