scheduling-and-queue
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of social media captions and media descriptions. It explicitly mitigates the risk of indirect prompt injection in the 'Safety & Confirmation Contract' (references/safety-and-confirmation.md) by instructing the agent to treat all post content as data, never as commands, and requiring the agent to surface suspicious instructions to the user rather than executing them.
- [COMMAND_EXECUTION]: The skill does not contain any instructions or scripts that execute arbitrary shell commands. All operations are strictly bounded to the authorized WoopSocial MCP tools.
- [DATA_EXFILTRATION]: No patterns of unauthorized data exfiltration were detected. The skill's network activity is limited to the WoopSocial API for its intended functionality (scheduling and publishing content).
- [CREDENTIALS_SAFE]: The skill does not request, store, or handle sensitive user credentials like passwords. It utilizes standard OAuth flows (oauth_create_authorization) as managed by the platform, ensuring secrets are handled through secure, established mechanisms.
- [SAFE]: The skill follows security best practices for AI agents, including mandatory human-in-the-loop confirmation for all irreversible actions and graceful degradation when external services are unavailable.
Audit Metadata