postedly-saved-correspondence
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Postedly records (drafts, contacts, and delivery reports), creating a surface where malicious instructions in that data could influence agent behavior.
- Ingestion points:
postedly_contacts,postedly_drafts, andpostedly_delivery_report(SKILL.md). - Boundary markers: The instructions do not specify delimiters or warnings to ignore embedded commands within the fetched data.
- Capability inventory: Tools such as
postedly_save_contact,postedly_save_draft, and search functions provide the ability to modify or interact with remote service data. - Sanitization: There is no mention of sanitizing or validating the contents of the correspondence before processing.
Audit Metadata