paid-ads
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to read and follow instructions from a local file (
.claude/product-marketing-context.md) to guide its campaign strategy. This creates an indirect prompt injection surface as the agent is not told to sanitize this input or treat it as untrusted data. - Ingestion points:
.claude/product-marketing-context.md(referenced in SKILL.md). - Boundary markers: Absent. There are no delimiters or warnings to ignore potentially malicious instructions embedded within the marketing context.
- Capability inventory: The skill is designed to interact with powerful advertising platform tools (Google Ads, Meta Ads, LinkedIn Ads, etc.) which typically have capabilities to modify account settings, budgets, and creative content.
- Sanitization: No validation or filtering is performed on the content of the marketing context file before it is used to influence the agent's actions.
Audit Metadata