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/clito download and execute the vendor's command-line interface directly from the NPM registry at runtime. - [COMMAND_EXECUTION]: The skill relies on the
Bashtool to run variousstophycommands 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 scrapecommand. - 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
Bashtool, 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