cold-email
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions and reference guides for writing emails. There are no scripts, binaries, or other executable files included.
- [NO_CODE]: No code is distributed with the skill, which prevents common attack vectors such as malicious logic or dependency vulnerabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by processing user input and reading a project context file, but it is assessed as safe because it lacks any high-privilege capabilities for exploitation. 1. Ingestion points: The skill ingests user responses to discovery questions and reads the
.claude/product-marketing-context.mdfile (SKILL.md). 2. Boundary markers: None are present to delimit untrusted input. 3. Capability inventory: The skill performs no network operations, file-system writes, or subprocess executions. 4. Sanitization: No input sanitization or validation is applied to the ingested text.
Audit Metadata