recycle-top-posts

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests historical social media post content, which acts as an untrusted data source. This presents a potential surface for indirect prompt injection if the retrieved posts contain instructions intended to influence the agent's behavior during the rewriting or scheduling process.
  • Ingestion points: Untrusted data enters the agent context through the list_posts_advanced, get_post_results, and get_post tools (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within the post content.
  • Capability inventory: The skill is capable of reading data via list_posts_advanced and get_analytics_summary, and writing data via bulk_create_posts (SKILL.md).
  • Sanitization: No explicit sanitization, validation, or escaping of the ingested post content is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 07:18 PM