The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a bash script scripts/crawlora.sh which executes curl to interact with the Crawlora API. This script correctly handles arguments using array expansion to prevent shell injection and provides a controlled interface for the agent to make network requests.
[EXTERNAL_DOWNLOADS]: The skill makes network requests to api.crawlora.net to retrieve app details and reviews. These operations target the vendor's official API infrastructure and are consistent with the skill's primary purpose.
[PROMPT_INJECTION]: The skill processes user-generated content in the form of app reviews from external stores. This presents a potential surface for indirect prompt injection if the agent interprets text within reviews as instructions.
Ingestion points: External data is ingested via scripts/crawlora.sh from the /appstore/reviews and /googleplay/reviews endpoints.
Boundary markers: The skill does not currently define explicit boundary markers or instruction-ignoring prompts for the ingested review data.
Capability inventory: The skill has capabilities for network operations (curl) and file system access as defined in the bash script.
Sanitization: The skill returns raw JSON from the API without specific text sanitization, relying on the agent's internal guardrails to handle the content.

app-review-mining