ionic-angular
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to analyze various local project files to determine the application's architecture and configuration.
- Ingestion points: The agent is instructed in SKILL.md (Step 1) to read local project configuration and source files, including package.json, main.ts, and routing modules, to auto-detect framework versions and architectural patterns.
- Boundary markers: No explicit instruction-ignoring delimiters or safety warnings are provided to prevent the agent from potentially following malicious instructions embedded within the analyzed project files.
- Capability inventory: While the agent uses the analysis results to generate code examples and explanations, there are no dangerous command execution or network exfiltration operations triggered by this ingested data within the skill's logic.
- Sanitization: The skill does not define any filtering, validation, or sanitization rules for the content read from the user's project files.
Audit Metadata