raqeeb
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
raqeebCLI tool to perform its core functions, including scanning local directories (raqeeb scan), auditing live URLs (raqeeb url), and applying automated fixes to source code (raqeeb fix). These operations are consistent with the skill's stated purpose as a development linter. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from external URLs and local project files to perform audits.
- Ingestion points: Reads content from local HTML/CSS files and fetches data from user-provided URLs.
- Boundary markers: None explicitly defined in the provided instructions.
- Capability inventory: Executes local CLI commands (
raqeeb), reads files, and has the ability to modify files via thefixcommand. - Sanitization: The skill relies on the
raqeebtool's internal logic to parse and report on code structure, which naturally limits the impact of embedded instructions, though the risk is inherent to any tool processing external content.
Audit Metadata