optimizing-popups
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather context from a local project file (.claude/product-marketing-context.md), which constitutes a potential surface for indirect prompt injection if the file content is controlled by an attacker.
- Ingestion points: Initial Assessment section in SKILL.md.
- Boundary markers: Absent; the agent is not warned to ignore instructions embedded within the context file.
- Capability inventory: None; the skill does not define any allowed tools, perform network operations, or execute shell commands.
- Sanitization: Absent; no validation or escaping is applied to the ingested content.
- [NO_CODE]: The skill consists entirely of markdown documentation and strategic advice without any executable scripts, tool calls, or binary files.
Audit Metadata