community-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies external context files (
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md) as data sources to be read by the agent at runtime. - Ingestion points:
SKILL.mdcontains logic instructing the agent to check for and read local context files to inform the community strategy. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat content within these files as untrusted or to ignore embedded instructions.
- Capability inventory: The skill defines no tool access in its frontmatter and performs no sensitive actions such as file writing, network exfiltration, or command execution across its documentation.
- Sanitization: No validation or sanitization mechanisms are specified for the external data ingested from the local environment.
Audit Metadata