The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the agentcash Node.js package from the public NPM registry to access its search functionality. Using the @latest tag ensures the most recent version is used but introduces a dependency on external code updates.
[COMMAND_EXECUTION]: The skill utilizes shell commands through npx agentcash@latest to perform network operations and fetch data from remote API endpoints hosted at stableenrich.dev.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external search results (news snippets, product descriptions), which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Search results fetched from https://stableenrich.dev/api/serper/* endpoints (e.g., news, shopping, images) as described in SKILL.md.
Boundary markers: There are no explicit delimiters or system instructions provided to help the agent distinguish between search results and legitimate instructions.
Capability inventory: The skill has access to shell command execution (npx) and network access for data retrieval.
Sanitization: No sanitization, filtering, or validation of the fetched external search content is defined in the instructions.

news-shopping