contentstudio
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from social media platforms via the social inbox commands, which could potentially contain malicious instructions. However, the skill implements strong mitigations by instructing the agent to perform dry-runs and obtain user confirmation for all mutating and customer-facing operations.
- Ingestion points: Social inbox triage commands in src/commands/inbox.ts.
- Boundary markers: Not explicitly defined for external content ingestion.
- Capability inventory: The skill provides comprehensive mutating tools for social media publishing and customer replies.
- Sanitization: No specific filtering of external social media content is performed.
- [COMMAND_EXECUTION]: The skill relies on the execution of the contentstudio CLI to interact with the platform's API. This is the primary and intended operation of the skill and is governed by strict safety rules in the SKILL.md file.
Audit Metadata