The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requests the Bash(infsh *) permission, which allows the agent to execute any subcommand of the infsh CLI tool. This is a broad permission required for the skill's primary function but grants significant control over the local command-line environment for that specific tool.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it extracts and processes untrusted data from external websites.
Ingestion points: External content is ingested via tavily/extract and exa/extract calls as described in SKILL.md.
Boundary markers: The workflow examples lack explicit boundary markers or instructions to ignore embedded commands, instead directly interpolating results into LLM prompts using placeholders like <search-results> and <content>.
Capability inventory: The skill uses Bash(infsh *) to execute search apps and pipe their output to other tools (e.g., OpenRouter LLMs).
Sanitization: There is no evidence of sanitization or validation of the web content before it is processed by the downstream agent or LLM.

web-search