The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses Glob and Grep to analyze local project files for existing StoreKit implementations. This creates a surface for indirect prompt injection, where malicious instructions hidden in the project's source code could potentially manipulate the agent's output during the generation process.
Ingestion points: Local project files targeted by Glob and Grep tools to detect existing code patterns.
Boundary markers: The instructions do not define specific delimiters or warnings to instruct the agent to ignore instructions embedded within the scanned files.
Capability inventory: The skill has Write, Edit, and Bash capabilities, which could be exploited if an injection successfully influences the agent.
Sanitization: There is no evidence of sanitization or filtering of the data retrieved from the scanned project files.
[COMMAND_EXECUTION]: The skill uses Bash to perform environmental checks, such as identifying if specific directories exist to determine the appropriate target path for the generated code.

promoted-iap