agent security skill risk: medium
AI File Trust Metadata Auditor
Defines commands and workflows for stamping, inspecting, auditing, and classifying provenance, trust scores, and compliance metadata on AI-generated or modified files using the AKF…
- Policy sensitive
- Human review
- External action: low
SKILL 1 file
SKILL.md
--- name: akf-trust-metadata description: "The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing." --- # AKF — The AI Native File Format Every photo has EXIF. Every song has ID3. AKF is the native metadata format for AI-generated content. ## When to Use Use this skill when you need to stamp, inspect, or audit provenance and trust metadata on AI-generated or AI-modified files for compliance, review, or handoff workflows. ## After creating or modifying files ```bash akf stamp <file> --agent <agent-name> --evidence "<what you did>" ``` Evidence examples: - "generated from user prompt" - "refactored existing code" - "tests pass" - "docs reviewed" ## Before modifying existing files ```bash akf read <file> # Check existing trust metadata akf inspect <file> # See detailed trust scores ``` ## Compliance auditing ```bash akf audit <file> --regulation eu_ai_act # EU AI Act Article 50 akf audit <file> --regulation hipaa # HIPAA akf audit <file> --regulation sox # SOX akf audit <file> --regulation nist_ai # NIST AI RMF ``` ## Classification - `--label confidential` for finance/secret/internal paths - `--label public` for README, docs, examples - Default: `internal` ## Install ```bash pip install akf ``` ## Links - https://akf.dev - https://github.com/HMAKT99/AKF - npm: `npm install akf-format` ## Limitations - Use this skill only when the task clearly matches the scope described above. - Do not treat the output as a substitute for environment-specific validation, testing, or expert review. - Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
REQUIRED CONTEXT
- file path
OPTIONAL CONTEXT
- agent name
- evidence description
- regulation name
- label value
ROLES & RULES
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
EXPECTED OUTPUT
- Format
- markdown
- Constraints
- use provided bash command examples
- respect limitations section
EXAMPLES
Includes bash command examples for akf stamp/read/inspect/audit plus evidence label examples.
CAVEATS
- Missing context
- Target audience or user role
- Expected AI response format after running commands
QUALITY
- OVERALL
- 0.55
- CLARITY
- 0.75
- SPECIFICITY
- 0.65
- REUSABILITY
- 0.25
- COMPLETENESS
- 0.55
IMPROVEMENT SUGGESTIONS
- Add explicit placeholders for dynamic inputs such as <file> and <agent-name>
- Define success criteria or verification steps after each command example
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- MoltPass Client for AI Agent Identitiesagentsecurity
- Supply Chain Dependency Risk Auditoragentsecurity
- Supply Chain Dependency Risk Auditoragentsecurity
- Threat Modeling Security Expertagentsecurity
- Security Bluebook Policy Builderagentsecurity
- Security Bluebook Policy Builderagentsecurity
- Security Blue Book Policy Builderagentsecurity
- Threat Modeling Security Architecture Expertagentsecurity
- Supply Chain Dependency Risk Auditoragentsecurity
- Threat Modeling Security Expertagentsecurity
- SIEM Detection Rule Tuning Guideagentsecurity
- AI File Metadata Compliance Auditoragentsecurity
- Azure Storage Misconfiguration Audit Reporteragentsecurity
- Implementing PAM for Database Accessagentsecurity
- AFL++ Coverage-Guided Fuzzing Procedureagentsecurity
- Supply Chain Attack Simulation Detectoragentsecurity
- Security Audit Fix Verifieragentsecurity
- Active Directory ACL Abuse Analyzeragentsecurity
- Privileged Access Workstation Implementation Guideagentsecurity
- SSRF Vulnerability Testing and Reporting Guideagentsecurity
- Security Audit Fix Revieweragentsecurity
- AWS IAM Privilege Escalation Detectoragentsecurity
- SSL/TLS Security Assessment with Sslyzeagentsecurity
- GCP Penetration Testing with GCPBucketBruteagentsecurity
- AWS CloudTrail Anomaly Detection Guideagentsecurity