plan-my-week
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from the user's social media history to establish content pillars and generate hooks, which could potentially expose the agent to malicious instructions embedded in that content. \n
- Ingestion points: Past social media posts referenced in the configuration step to identify topics and style. \n
- Boundary markers: The skill does not define specific delimiters or instructions to ignore instructions found in the processed data. \n
- Capability inventory: The skill utilizes tools such as
schedule_postto interact with external publishing queues. \n - Sanitization: The skill enforces a mandatory human approval workflow where each post must be individually reviewed and confirmed with a unique code, preventing automated execution of injected commands.
Audit Metadata