manage-ambush-feeds
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and configuration do not exhibit malicious patterns or attempts to exfiltrate sensitive data. Instructions specifically forbid harvesting bearer tokens.
- [PROMPT_INJECTION]: The skill processes user monitoring requests and external news items.
- Ingestion points: User requests for feed creation/updates and content from news feed emissions (SKILL.md).
- Boundary markers: The skill instructs the agent to explain policy restrictions rather than bypassing them and requires explicit confirmation for destructive delete operations.
- Capability inventory: MCP tools are limited to feed lifecycle management and emission history retrieval.
- Sanitization: The instructions emphasize accurate summarization of structured payloads and identifying feeds by IDs to avoid naming ambiguity.
- [EXTERNAL_DOWNLOADS]: Connects to the Ambush Feeds MCP server at api.ambush.ai to facilitate news management. This connection is standard for the skill's intended purpose and uses the vendor's official infrastructure.
Audit Metadata