plan-content-calendar

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs standard content management tasks using the vendor's own tools (list_posts_advanced, get_queue, bulk_create_posts). The operations are consistent with the stated purpose of planning a content calendar.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted user input to draft social media posts. 1. Ingestion points: Step 1 asks for the user's topic or goal (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified. 3. Capability inventory: The skill can call 'bulk_create_posts' to write content to the service (SKILL.md). 4. Sanitization: The risk is mitigated by a mandatory human-in-the-loop review process defined in Step 5, which requires the agent to 'Present it as a table' and 'Ask the user to confirm or change it' before proceeding to creation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 07:17 PM