corroboration-skill-builder
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides educational templates and prompts for historical thinking without any malicious code or security vulnerabilities.- [PROMPT_INJECTION]: The instructions are strictly pedagogical and do not attempt to manipulate or bypass AI safety guardrails or system instructions.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided content such as historical topics and student levels (SKILL.md). While this creates an ingestion surface, the skill lacks dangerous capabilities like network access or file system writes, and the instructions are limited to text generation, which mitigates the risk of malicious exploitation.- [COMMAND_EXECUTION]: No shell commands, script execution, or dynamic context injection patterns (such as
!command) were identified in the skill body or metadata.
Audit Metadata