stophy-jobs

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill employs npx @stophy/cli to download and execute the vendor's command-line interface directly from the NPM registry at runtime.
  • [COMMAND_EXECUTION]: The skill relies on the Bash tool to run various stophy commands for web scraping and interacting with job board APIs.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted job postings and company reviews from external sources such as LinkedIn, Indeed, and Upwork. This creates a surface where an attacker could embed malicious instructions in a job description to influence the agent's behavior during processing.
  • Ingestion points: Data retrieved from job boards and career pages using the stophy scrape command.
  • Boundary markers: The skill instructions do not specify any delimiters or special handling to separate external content from the agent's internal instructions.
  • Capability inventory: The agent has access to the Bash tool, allowing it to perform local operations.
  • Sanitization: No sanitization or filtering of the scraped content is described, meaning any embedded instructions are passed directly to the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 09:19 PM