blog-idea-generator
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted data from multiple project files to generate content.
- Ingestion points: The skill reads project documentation in
SKILL.mdincludingdocs/en/company-profile.md,docs/en/services.md,docs/en/pages.md,docs/sector-brief.md,docs/style-brief.md,docs/blogs/topics.md, andsrc/pages/en/blog/. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested files specified in
SKILL.md, increasing the risk of the agent following malicious instructions found in documentation. - Capability inventory: The skill possesses file-write capabilities as defined in
SKILL.md(Step 7), specifically writing todocs/blogs/topics.md. - Sanitization: No sanitization, escaping, or validation of the external content is performed before interpolation into the generation prompt.
Audit Metadata