email-sequence
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions the agent to ingest data from a local file
.claude/product-marketing-context.mdto tailor its email sequence suggestions.\n - Ingestion points: SKILL.md (reads
.claude/product-marketing-context.md).\n - Boundary markers: Absent; there are no specific delimiters defined for this context file.\n
- Capability inventory: None; the skill consists only of instructional markdown and does not include scripts or tool-execution logic.\n
- Sanitization: Absent; the content from the local context file is used directly.\n- [NO_CODE]: The skill consists entirely of Markdown files providing strategy, templates, and best practices, without any executable scripts, system commands, or remote code patterns.
Audit Metadata