popups
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The instructions direct the agent to ingest product marketing context from external files, which creates a potential surface for indirect prompt injection if those files are controlled by an attacker.
- Ingestion points: The skill instructs the agent to read
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md(SKILL.md). - Boundary markers: There are no instructions provided to delimit the ingested content or to disregard embedded instructions within those files.
- Capability inventory: The skill does not define any internal scripts, subprocess calls, or specific network tools; however, it relies on the agent's default environment capabilities.
- Sanitization: No sanitization, escaping, or validation steps are defined for the data ingested from the external markdown files.
- [NO_CODE]: The skill consists entirely of markdown instructions and evaluation data. It contains no executable scripts (e.g., .py, .js, .sh), binary files, or configurations that trigger automated code execution.
Audit Metadata