skills/garethmanning/education-agent-skills/media-literacy-deconstruction-protocol/Gen Agent Trust Hub
media-literacy-deconstruction-protocol
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No evidence of malicious code, obfuscation, or unauthorized data access was found in the skill definition.
- [SAFE]: The skill does not include any external downloads, package installations, or remote code execution patterns.
- [SAFE]: The skill does not attempt to escalate privileges, modify system configurations, or establish persistence.
- [SAFE]: The skill ingests untrusted user data via template variables such as
{{specific_text}}and{{student_profiles}}. While the prompt lacks explicit boundary markers (e.g., XML tags) or sanitization to isolate this data, the skill does not have access to tools, network operations, or the file system, which effectively eliminates the risk of an exploitable indirect prompt injection attack.
Audit Metadata