schedule-posts

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of instructional content and metadata within the SKILL.md file and does not include any executable scripts or binary files.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided content from external sources such as CSV files or spreadsheets for social media scheduling.
  • Ingestion points: Untrusted data enters the agent context through the bulk_schedule tool via rows or csv parameters (SKILL.md).
  • Boundary markers: The instructions explicitly require a dry run for batches to show the user preview data and a final confirmation step ("Nothing is queued without a yes") for single posts before execution.
  • Capability inventory: The agent can perform network operations to schedule posts, list queues, and cancel tasks via the PostWire API.
  • Sanitization: The skill specifies that every post must be checked against network-specific rules (e.g., character limits, media requirements) before being queued.
  • [DATA_EXPOSURE]: The skill references the use of an API key (POSTWIRE_API_KEY) for authentication.
  • It includes a clear security directive: "Never print the key," which serves to prevent the agent from leaking sensitive credentials in its output or logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 04:09 PM