04-weekly-plan
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external sources to generate content recommendations and rationale.
- Ingestion points: The skill reads from Notion databases including
╣ {Client} w Strategy,Idea Pool(defined in${CLAUDE_PLUGIN_ROOT}/reference/notion-schema.md), andPosts DB. - Boundary markers: There are no specific instructions or delimiters defined to isolate the content of the Idea Pool cards or strategy sections from the system prompt instructions.
- Capability inventory: The skill has the capability to write to the
╥ Weekly PlansNotion table and send data to an external Telegram channel (viachat_idconfiguration). - Sanitization: The skill lacks explicit sanitization or validation logic for the content retrieved from the Notion tables before it is summarized and sent to the Telegram digest.
Audit Metadata