stophy-docs
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape and read content from external documentation websites which are untrusted sources.
- Ingestion points: Web content is ingested into the agent context via the
stophy scrapecommand inSKILL.md. - Boundary markers: The skill instructions do not specify the use of delimiters or specific instructions to ignore embedded commands within the scraped text.
- Capability inventory: The agent has the capability to execute shell commands using the
stophyCLI andnpx. - Sanitization: There is no evidence of sanitization or filtering of the scraped content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto fetch and execute the@stophy/clipackage from the NPM registry. - Evidence: The
allowed-toolssection and documentation refer tonpx @stophy/cliandnpx @stophy/cli@latest. - [COMMAND_EXECUTION]: The skill instructions direct the agent to execute various subcommands of the
stophyutility, such assearch,map, andscrape. - Evidence: Examples provided in the Quick Start section of
SKILL.mddemonstrate direct shell execution of the CLI tool.
Audit Metadata