The Agent Skills Directory

[PROMPT_INJECTION]: This skill presents an indirect prompt injection surface as it is designed to process and rewrite user-provided text. 1. Ingestion points: User content is ingested via the command arguments and pasted text sections described in SKILL.md. 2. Boundary markers: The instructions do not define clear boundaries or isolation for user-provided data. 3. Capability inventory: No dangerous tools, shell commands, or network operations are defined; the skill is limited to text generation. 4. Sanitization: No input validation or sanitization is present.
[NO_CODE]: No scripts, executables, or package manifests were found in the skill files.

social-presence