community-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read content from external files, which creates a potential vulnerability if those files contain malicious instructions.
- Ingestion points: The agent is instructed in
SKILL.mdto read.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdto gather context about the user's product. - Boundary markers: Absent. The instructions do not define specific delimiters or provide warnings to the agent to disregard instructions potentially embedded within these marketing context files.
- Capability inventory: The skill is primarily intended for generating marketing strategy text. No capabilities for shell command execution, file system modification, or network requests were found in the skill's instructions or associated files.
- Sanitization: Absent. There is no evidence of logic intended to filter, escape, or validate the content of the marketing context files before they are processed by the agent.
Audit Metadata