blog-audit
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection as it ingests content from Markdown and HTML files in the project directory to perform audits.
- Ingestion points: Reads file content from user-controlled directories such as
content/,posts/, andblog/(found inSKILL.md). - Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions embedded within the processed blog files.
- Capability inventory: The agent has the ability to read files, spawn parallel subagents using the
Tasktool, and write the aggregated results toblog-audit-report.mdin the project root. - Sanitization: Absent; the skill lacks logic to sanitize or escape data before it is processed by the Content Quality, SEO, and AI Readiness subagents.
Audit Metadata