x-tech-articlewriter
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8). This vulnerability exists because the skill processes external input without adequate isolation.
- Ingestion points: The workflow in
SKILL.mdinstructs the agent to "Analyze the source material (links, docs, or ideas)". - Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within analyzed data, increasing the risk that instructions inside the source material could override agent logic.
- Capability inventory: The skill uses the
generate_imagetool and produces structured text articles, providing a surface for data manipulation or tool misuse. - Sanitization: No evidence of input validation or sanitization of external content is present in the skill files.
- EXTERNAL_DOWNLOADS (LOW): The
README.mdfile directs users to install the skill vianpx skills add felixondesk/agent-skills. This repository belongs to an untrusted GitHub user not on the primary trusted organizations list, representing an unverified dependency risk.
Audit Metadata