planning-launches
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and strategy frameworks. It does not include any executable scripts, tool configurations, or command-line instructions.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions include reading a local file
.claude/product-marketing-context.mdto gather context before responding. While this file could theoretically contain malicious instructions, the skill possesses no capabilities (such as network access, file writing, or command execution) that could be leveraged for an attack.\n - Ingestion points:
.claude/product-marketing-context.md(read instruction in SKILL.md)\n - Boundary markers: Absent; the agent is instructed to read the file content directly.\n
- Capability inventory: None; the skill provides strategic advice and does not perform file writes, network operations, or command execution.\n
- Sanitization: Absent
Audit Metadata