blog-idea-generator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface where it ingests untrusted data from various files in the repository to inform its ideation process. If these files were to contain malicious instructions, they could potentially influence the agent's output or behavior.
- Ingestion points: The skill is instructed to read multiple files in the
SKILL.mdfile (Step 1), includingdocs/en/company-profile.md,docs/en/services.md,docs/en/pages.md,docs/sector-brief.md,docs/style-brief.md,[topic-ideas](../blog-writer/references/topic-ideas.md), and existing blog articles within thesrc/pages/en/blog/directory. - Boundary markers: Absent. There are no explicit instructions to the agent to use delimiters or to disregard embedded instructions within the ingested documents.
- Capability inventory: The skill has read access to the local file system and write capabilities, specifically for saving its output to the
../blog-writer/references/topic-ideas.mdpath. - Sanitization: Absent. The skill does not implement specific filtering or sanitization logic for the content it reads from the documentation files.
Audit Metadata