opened-daily-newsletter-writer

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from Notion and external URLs, creating a surface for indirect prompt injection. 1. Ingestion points: Notion collection search (collection://5d0c1ad8-e111-4162-91da-2cac9bd1269b) and source material URLs. 2. Boundary markers: None specified in the instructions to delimit untrusted content. 3. Capability inventory: Filesystem operations (mkdir, cp), Notion search, and automated HubSpot draft creation via internal tools. 4. Sanitization: No input validation or sanitization is performed on ingested data. Mitigation: The risk is mitigated by a mandatory human approval step (Checkpoint 1) before the newsletter is drafted.
  • [COMMAND_EXECUTION]: The skill uses local shell commands including mkdir to create project directories and cp to archive final newsletter files within the local workspace environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 11:24 AM