skills/garethmanning/education-agent-skills/pedagogical-content-knowledge-developer/Gen Agent Trust Hub
pedagogical-content-knowledge-developer
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of a markdown configuration file (SKILL.md) containing YAML frontmatter and a structured prompt template. It does not include any executable code, shell scripts, or binary files.
- [REMOTE_CODE_EXECUTION]: No patterns for remote code execution were found. The skill does not use tools like curl, wget, or any programming language execution environments (Python, Node.js) to fetch or run external content.
- [DATA_EXFILTRATION]: There are no network-capable operations or instructions that access sensitive system files, credentials, or environment variables. The data flow is restricted to generating a text response based on user-provided pedagogical context.
- [PROMPT_INJECTION]: The prompt uses standard variable interpolation for user inputs (
{{teaching_context}}, etc.). While it lacks strict boundary markers for these inputs, the risk is negligible as the skill lacks any capabilities (like tool use or file modification) that an injected prompt could exploit. - [EXTERNAL_DOWNLOADS]: The skill does not define any external dependencies or download any third-party packages. All referenced 'evidence sources' are legitimate academic publications used for instructional context.
Audit Metadata