capacitor-plugin-spm-support
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests content from local files (package.json, .podspec, and Swift source files) and uses that data to perform code generation, file system modifications, and command execution.
- Ingestion points: reads package.json, .podspec, and Swift classes from the plugin root directory.
- Boundary markers: Absent; there are no instructions to the agent to treat file content as data rather than instructions.
- Capability inventory: Includes file reading, file creation/writing, file deletion, and shell command execution (e.g., npx cap sync, build commands).
- Sanitization: Absent; the skill does not specify any validation or sanitization steps for the data retrieved from local files.
- [COMMAND_EXECUTION]: The skill instructs the agent to run shell commands including npx cap sync and dependency installation using the repository's package manager. While these are standard development tasks, they are executed based on context gathered from potentially untrusted local files.
Audit Metadata