The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the @useclawlink/cli tool via npx to perform various Apify actions including running actors, fetching dataset items, and retrieving logs.
[EXTERNAL_DOWNLOADS]: The skill downloads and runs the @useclawlink/cli package from the NPM registry. As this is the official package provided by the skill author (clawlink-hq), it is considered a legitimate dependency.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill manages its own authentication credentials by storing them in a local file at ~/.clawlink/credentials.json. This is the documented and standard behavior for this vendor's tools.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as Apify datasets and logs, which could theoretically contain instructions intended to influence the agent.
Ingestion points: apify_get_dataset_items, apify_get_key_value_record, and apify_get_log actions (SKILL.md).
Boundary markers: Not explicitly provided in the skill instructions.
Capability inventory: Shell command execution via the CLI tool (SKILL.md).
Sanitization: No specific sanitization or filtering logic is described in the skill.

apify