content-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project context files, creating a potential surface for indirect prompt injection if those files are compromised.
- Ingestion points: Reads
.claude/project-context.mdand.cursor/project-context.md(specifically Sections 3, 4, and 11) as identified in the 'Initial Assessment' phase. - Boundary markers: The instructions do not provide explicit delimiters or "ignore instructions" warnings when processing these files.
- Capability inventory: The skill is primarily focused on text generation, strategy planning, and referencing other content-specific skills; it does not perform network operations or command execution.
- Sanitization: There is no mention of sanitizing or validating the input from these files before using it to generate marketing strategies.
Audit Metadata