stophy-ads
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill executes code from a remote source via
npx @stophy/cli@latest. This command downloads and runs the most recent version of the Stophy CLI from the public NPM registry at runtime. - [EXTERNAL_DOWNLOADS]: The skill's operation depends on fetching the
@stophy/clipackage from the NPM registry. - [COMMAND_EXECUTION]: The skill uses Bash tools (specifically
stophy scrape) to interact with the environment and perform its scraping tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions.
- Ingestion points: Data is ingested from public advertisement libraries (Google, Meta, TikTok, LinkedIn) which contain arbitrary text and media descriptions.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the agent processes the scraped advertisement content.
- Capability inventory: The skill has Bash execution capabilities used to run the scraper and process its output.
- Sanitization: There is no mention of sanitization, validation, or filtering of the external content before it is presented to the agent.
Audit Metadata