article-deconstructor
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it is designed to analyze arbitrary article content provided by users. Ingestion points: Untrusted articles enter the agent context via the workflow defined in SKILL.md. Boundary markers: The instructions do not include boundary markers or explicit directives for the agent to ignore instructions within the input text. Capability inventory: The skill is limited to text analysis and report generation and has no access to network, filesystem, or execution tools. Sanitization: No input validation or filtering is specified for the articles being processed.
- [NO_CODE]: This skill consists entirely of Markdown instructions and reference documents. No executable code, shell scripts, or external package dependencies are included in the skill files, which minimizes the attack surface.
Audit Metadata