flutter-app-discovery
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from an external Flutter project (such as
pubspec.yamland Dart source files) and includes findings in a summary report. This creates a surface where malicious strings in the project files could influence agent behavior. - Ingestion points: The skill reads
pubspec.yaml,analysis_options.yaml, Dart source files inlib/, and native configuration files likeAndroidManifest.xmlandInfo.plist(inSKILL.md). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the ingested data as untrusted text.
- Capability inventory: The skill has read access to the project filesystem and the ability to write an audit report to
docs/audit/codebase_discovery.md(inSKILL.md). - Sanitization: No sanitization or escaping of the external content is performed before interpolation.
- [SAFE]: The skill implements a read-only methodology for project discovery and reconnaissance. It explicitly forbids file modifications during the audit process and focuses on extracting metadata and architectural patterns to assist the user.
Audit Metadata