The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified. The skill follows its stated purpose of facilitating market research and report production.- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to its research workflow. Ingestion points: Untrusted data enters the context during 'deep web research' (SKILL.md). Boundary markers: Absent. Capability inventory: The skill performs file writes for report generation and invokes a LaTeX compiler (SKILL.md). Sanitization: Absent. As this is an inherent risk of research-oriented tasks, it does not escalate the verdict.- [COMMAND_EXECUTION]: The workflow mentions 'PDF generation via LaTeX compiler'. This involves executing local document preparation binaries, which is expected functionality for a skill focused on professional report formatting.

market-research