stophy-download
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill downloads content from arbitrary external websites and saves it as markdown files, creating a surface for indirect prompt injection if the agent later processes these files.
- Ingestion points: External URLs provided to the
stophy crawlcommand inSKILL.mdexamples. - Capability inventory: The skill uses
Bashto create directories (mkdir) and write files (> "bun-docs/$name.md"). - Boundary markers: No specific delimiters or instructions are provided to help the agent distinguish between its own instructions and the content downloaded from the web.
- Sanitization: The skill performs filename sanitization using
sed, but does not sanitize the markdown content itself. - [COMMAND_EXECUTION]: The skill executes shell commands to perform its primary functions, including site crawling and JSON processing.
- Evidence: Core logic in
SKILL.mdusesstophy,jq,sed, andbashcontrol structures. - Note: These commands are used as intended for the skill's purpose, and the
allowed-toolsmetadata restricts the environment to the author's specific CLI tools.
Audit Metadata