tinyfish-cli
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill requires the installation of the
cli-anything-tinyfishPython package. This package is provided by the skill author and is the core binary used to interact with the TinyFish APIs. - [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
cli-anything-tinyfishtool to search the web, fetch markdown content, and run natural-language browser automations. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external web sources.
- Ingestion points: Data from external websites is brought into the agent's context through the stdout of
cli-anything-tinyfish searchandcli-anything-tinyfish fetchcommands. - Boundary markers: No specific delimiters or instructions are provided to the agent to treat fetched content as untrusted data or to ignore embedded instructions.
- Capability inventory: The agent can perform network requests and complex browser interactions (clicking, form filling) using the CLI tool.
- Sanitization: The skill does not implement or document any sanitization or validation logic for the content retrieved from remote URLs.
Audit Metadata