launch-runbook
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed exclusively of instructional Markdown files and a YAML configuration file. It does not include any scripts, binaries, or automated tasks that could execute code on the host system.- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection by instructing the agent to read an external file (
.agents/marketing-context.md). - Ingestion points: Reads
.agents/marketing-context.mdas a 'truth file' for context (SKILL.md). - Boundary markers: No explicit delimiters or boundary instructions are provided to separate the context file from the agent's instructions.
- Capability inventory: The skill defines no capabilities; there are no tool calls, network requests, or shell executions allowed or referenced.
- Sanitization: No evidence of input sanitization or filtering is present.
- Note: Despite the ingestion point, the lack of functional capabilities (tools) makes this surface non-exploitable for data exfiltration or system modification.
Audit Metadata