The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted user input during requirements gathering to generate security documentation. Ingestion points occur during interactive user sessions (SKILL.md). The instructions do not define specific delimiters or boundary markers for segregating user input within the agent's context. The skill is instructional and does not possess direct file-system, network, or code execution capabilities. No specific sanitization or validation logic is provided for the input processed by the agent.- [SAFE]: The skill implements a security-focused workflow that encourages the proactive identification of vulnerabilities and the deterministic evaluation of features for deep security review based on their technical impact.- [NO_CODE]: The skill consists entirely of instructional markdown and YAML metadata, without any scripts, executables, or code-based logic.

security-gate