dev-context-engineering
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides utility scripts for repository documentation analysis (
scan_context_artifacts.py,query_context_graph.py,validate_context_graph.py) which operate locally and do not perform network requests or unauthorized file modifications. - [SAFE]: The skill includes security-enhancing assets, such as GitHub Action workflows for PII (Personally Identifiable Information) detection and compliance rules for FCA-regulated environments.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process documentation from a target repository. This creates a surface for indirect prompt injection if the scanned files contain malicious instructions.
- Ingestion points:
scan_context_artifacts.pycrawls the repository file system;validate_context_graph.pyandquery_context_graph.pyread the generatedcontext-graph.json. - Boundary markers: The scripts do not explicitly use delimiters or ignore directives for content extracted from repository files.
- Capability inventory: The Python scripts perform file reads and JSON parsing, outputting analysis results to the console or local files.
- Sanitization: Content is parsed using standard
json.loadsand regex patterns; no explicit sanitization of processed strings is present. - [EXTERNAL_DOWNLOADS]: The documentation references established development tools and frameworks such as GitHub Spec Kit, Anthropic Agent Skills, and OpenSpec. These are well-known industry resources and do not represent a security risk.
Audit Metadata