launch-post
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructions for natural language generation. It does not include any scripts, binaries, or tool configurations that interact with the host system or external networks.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted user input describing a product or tool.
- Ingestion points: The 'Required Inputs' section (e.g., 'What you built', 'Proof') in SKILL.md.
- Boundary markers: Absent from instructions.
- Capability inventory: None; the skill has no access to subprocesses, file-writing, or network tools.
- Sanitization: None; the skill interpolates input directly into text templates. Because the skill lacks the ability to execute code or exfiltrate data, this ingestion surface does not represent a functional security risk.
Audit Metadata