blog-audit
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection vulnerabilities due to the processing of external content from project files.
- Ingestion points: The skill identifies and reads content from markdown, MDX, and HTML files across various directories such as content/, posts/, and articles/.
- Boundary markers: There are no explicit instructions or delimiters defined to prevent subagents from executing instructions that might be embedded within the blog post content being analyzed.
- Capability inventory: The skill utilizes powerful tools including Bash, Write, and the Task orchestration tool, which represent a significant attack surface if an agent is successfully manipulated via injected content.
- Sanitization: No sanitization or content validation is performed on the files prior to analysis by the subagents.
Audit Metadata