blog-to-linkedin-repurposer
Fail
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: CRITICALPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process external content (text or URLs) to generate marketing posts, creating a surface for indirect prompt injection.
- Ingestion points: The skill defines inputs as pasted text or URLs from the user in
SKILL.md. - Boundary markers: The workflow lacks explicit instructions to isolate input data or to ignore embedded instructions within the source blog post.
- Capability inventory: The skill does not have any allowed tools or shell execution capabilities, which limits the potential impact of an injection.
- Sanitization: No sanitization or validation logic is defined for the input content.
- [EXTERNAL_DOWNLOADS]: Automated security scanners flagged the domain
Builder.org, which is listed as the skill's author, as a malicious or blacklisted URL. - While the domain is part of the metadata and not a functional resource downloaded during execution, its presence indicates a low-reputation source.
- [NO_CODE]: The skill consists entirely of markdown documentation and instructional logic. It does not include any Python or Node.js scripts, configuration files for package managers, or binary executables.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata