export
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from user conversation summaries and memory files during export operations.\n
- Ingestion points: Data is sourced from SQLite sessions and group
CLAUDE.mdfiles as specified inSKILL.md.\n - Boundary markers: The skill does not explicitly define markers to prevent interpretation of instructions within the exported data, though the data is stored statically.\n
- Capability inventory: Access is limited to
read_file,write_file, andlist_dirtools.\n - Sanitization: The instructions mandate the redaction of secrets and sensitive details in configuration and security event exports.
Audit Metadata