The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external competitor websites, customer reviews, and emails, creating a surface for indirect prompt injection where an attacker could place malicious instructions in scraped content. Ingestion points: Found in SKILL.md (Instructions and Data Sources section) and references/skill-contract.md (Core Invariants 3). Boundary markers: The skill includes explicit instructions in SKILL.md and references/skill-contract.md to treat external data as untrusted input and to ignore any embedded instructions. Capability inventory: The skill provides markdown-based instructions only and contains no executable scripts, executables, or commands within the skill files. Sanitization: Relies on instructions-based mitigation to distinguish evidence from instructions.
[SAFE]: No obfuscation, malicious persistence mechanisms, or unauthorized credential handling were detected. The skill follows best practices by requiring user authorization for any external side effects or persistent writes and advising against storing API keys in source control.

competitor-profiling