The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like curl to fetch content from external URLs provided by the user.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of several third-party Python packages, including playwright, Pillow, and numpy, for its core rendering and image processing tasks.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill performs network requests to non-whitelisted domains such as r.jina.ai and defuddle.md to retrieve web content for card generation.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests untrusted data from external websites and incorporates it into its summary and rendering process. * Ingestion points: Content fetched from arbitrary external URLs via the curl command. * Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate embedded instructions within the fetched text. * Capability inventory: The skill can write to the local filesystem, execute shell commands, and run Python scripts. * Sanitization: No explicit sanitization or validation of the fetched content is performed; the skill relies on the LLM to summarize the data into a fixed template.

qiaomu-info-card-designer