email-sequence
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill automatically loads and processes content from several local files which serves as a potential vector for indirect prompt injection if those files are tampered with.
- Ingestion points: The skill reads brand profiles, compliance rules, manifests, templates, and Agency SOPs from
~/.claude-marketing/subdirectories. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between administrative data and potentially untrusted instructional content within these files.
- Capability inventory: The skill is designed for output generation only and does not possess capabilities for file writing, network operations, or shell command execution, which significantly limits the potential impact of an injection.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the content loaded from the brand and SOP directories.
Audit Metadata