stophy-jobs
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npx -y @stophy/cliwithin its allowed tools and instructions, which downloads and executes the author's command-line interface tool from the NPM registry at runtime. - [COMMAND_EXECUTION]: The skill requires the ability to execute shell commands via
Bashto run thestophyCLI for job searching, data retrieval, and account authentication. - [INDIRECT_PROMPT_INJECTION]: The primary function of the skill is to ingest and process data from external, untrusted sources including Google Jobs, LinkedIn, Indeed, Upwork, and various company careers pages. Maliciously crafted job postings on these platforms could potentially contain instructions aimed at influencing the agent's logic.
- Ingestion points: Commands such as
stophy <source> job <url>andstophy careers job <url>fetch full descriptions from remote URLs into the agent's context. - Boundary markers: The instructions do not specify the use of delimiters or warnings to the agent to disregard embedded instructions within the job postings.
- Capability inventory: The agent has access to the
Bashtool to execute system commands. - Sanitization: There is no evidence of sanitization or filtering applied to the fetched job descriptions before they are processed by the agent.
Audit Metadata