stophy-scrape

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's primary function is to scrape and process content from arbitrary, untrusted web URLs. This content is introduced into the agent's context, creating a surface for indirect prompt injection attacks where a malicious website could attempt to hijack the agent's behavior.\n
  • Ingestion points: Content is fetched from user-provided or discovered URLs via the stophy scrape command.\n
  • Boundary markers: No explicit instruction delimiters or sanitization steps for the scraped content are mentioned in the skill definition.\n
  • Capability inventory: The skill can execute shell commands through the Stophy CLI and has the ability to write scraped content to the local filesystem using the -o flag.\n
  • Sanitization: None documented; the tool relies on the underlying LLM's guardrails to handle potentially malicious content in the scraped data.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes npx @stophy/cli, which involves downloading and running code from the NPM registry. This is identified as a vendor-provided tool corresponding to the skill's author.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute stophy CLI commands. The allowed-tools configuration in the frontmatter restricts execution to these specific vendor commands, providing a layer of control over the execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 09:19 PM