talktoads
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires connection to a remote Model Context Protocol (MCP) server at
https://talktoads.com/mcp. This server provides the operational tools to interface with the Meta Ads API. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Meta Ads platform, such as ad names, creative content, and review feedback, which could contain malicious instructions. The risk is mitigated by instructions requiring the agent to seek explicit user confirmation before performing sensitive actions like raising budgets or going live.
- Ingestion points:
list_ads,get_performance,list_ad_accounts(fetching data from Meta APIs via the MCP server). - Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded in the retrieved ad data.
- Capability inventory:
create_campaign,update_budget,go_live,pause,set_spend_cap. - Sanitization: None; the skill reports numbers and text as they are returned from the API.
Audit Metadata