The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted content from the user's local project files (e.g., Podfile, Info.plist, source code) to map the project structure. Malicious instructions embedded in these files could theoretically influence the agent's behavior during the integration process.
Ingestion points: Uses readFile and fileSearch on project files like Podfile, Package.swift, Info.plist, and source code (e.g., AppDelegate.swift).
Boundary markers: No explicit instructions are provided to the agent to ignore or delimit embedded instructions within the project files it reads.
Capability inventory: The skill utilizes executeBash and file writing capabilities to perform the integration.
Sanitization: No specific sanitization or validation of the content read from files is defined before the agent uses it to plan its next steps.

cometchat-ios