capacitor-plugin-spm-support
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files which could theoretically contain malicious instructions designed to influence the agent's output or actions.
- Ingestion points: The procedure requires reading
package.json,.podspec, and Swift source files (ios/) in Step 1. - Boundary markers: No specific delimiters or boundary markers are defined to isolate the content of these files from the agent's primary instructions.
- Capability inventory: The skill has the capability to write files (
Package.swift), modify existing source code, delete files (Objective-C bridge files), and execute shell commands (npx cap sync). - Sanitization: There is no mention of sanitizing or validating the content extracted from the ingested files before it is used to generate code or parameters for command execution.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands as part of the verification process.
- Evidence: Step 6 involves running
npx cap syncor a repository-specific equivalent within the example or test app directory.
Audit Metadata