direct-mail
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and strategy templates for B2B direct mail campaigns. There are no scripts, binaries, or command-line executions provided within the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read from a local file,
.agents/sales-context.md, to gain context about the sales environment. While this represents a data ingestion point, the skill performs no high-risk operations (such as code execution or network exfiltration) with the data, making the attack surface negligible. - Ingestion points:
.agents/sales-context.md(SKILL.md) - Boundary markers: Absent. The skill expects the agent to load the file content directly into context.
- Capability inventory: No tool invocations, subprocess calls, or network operations are defined in this skill.
- Sanitization: Absent; the skill relies on the underlying model's standard handling of local context files.
Audit Metadata