YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]
- Category
- YARA Match
- Confidence
- 80% confidence
- Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
- Content
md --- name: reelsfarm-ai-avatars description: Generate AI images of fictional people for marketing creatives with ReelsFarm (GPT Image, Nano Banana, Seedream, FLUX 3), start from reference templates, and edit results in follow-up turns. Needs a ReelsFarm account. metadata: openclaw: emoji: "🧑🎤" homepage: https://reelsfarm.com/docs/mcp primaryEnv: REELSFARM_API_KEY requires: bins: - reelsfarm env: - REELSFARM_API_KEY envVars: - name: REELSFARM_API_KEY required: true description: ReelsFarm MCP API key (starts with rfmcp_), created in the MCP tab of
