The Agent Skills Directory

[SAFE]: The skill is entirely focused on a voting and feedback workflow using a specific project management CLI tool called 'probe'. No malicious command execution or exfiltration patterns were detected.\n- [PROMPT_INJECTION]: The skill ingests external data from 'directives' and 'ideas' via the 'probe' tool. While this creates a surface for indirect prompt injection, it is an inherent property of the task and is considered a low risk managed by standard agent guardrails.\n
Ingestion points: SKILL.md (retrieving data via probe message directives and probe idea get <id>)\n
Boundary markers: Absent\n
Capability inventory: probe idea vote, probe message send\n
Sanitization: Absent

zeno-voting