web-search
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute local scripts (tavily.sh,firecrawl.sh) with parameters derived from user input (search queries and URLs). While this is the intended functionality of the skill, it relies on the underlying shell scripts to safely handle and sanitize these arguments to prevent command injection. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it fetches and processes arbitrary content from the public web.
- Ingestion points: Untrusted data enters the agent context via
WebFetch,Tavilysearch results, andFirecrawlscrapes (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious directions embedded within the fetched web content.
- Capability inventory: The skill has access to the
Bashtool, allowing it to execute local scripts and potentially interact with the file system or network based on instructions received. - Sanitization: There are no documented sanitization or validation steps for the content retrieved from external URLs before it is processed by the agent.
Audit Metadata