60-launch-playbook
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a set of instructional templates for the agent. It does not contain any executable scripts, binaries, or shell commands. It does not perform network operations or access sensitive environment variables or local system files.
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to process external data sources such as GTM plans and campaign briefs. An analysis of the attack surface follows:
- Ingestion points: Reads 'GTM plan' and 'campaign brief' provided by the user (SKILL.md).
- Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands in the source documents.
- Capability inventory: The skill is restricted to generating markdown text output. It has no capabilities for network exfiltration, subprocess execution, or sensitive file system access.
- Sanitization: Absent; the skill relies on the underlying model's safety protocols.
- Risk Assessment: Because the skill lacks any privileged capabilities, the risk of indirect prompt injection is negligible, and the finding is classified as safe.
Audit Metadata