The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute mcpc, jq, and gh CLI commands as part of its documented workflow. These commands are used to interact with Apify services and report structural issues to a vendor-owned GitHub repository.
[EXTERNAL_DOWNLOADS]: The skill documentation recommends installing the @apify/mcpc package from the official NPM registry if it is not found on the system. As a well-known package from an established service, this is a standard configuration step.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data scraped from the web via various Apify Actors.
Ingestion points: Data enters the agent's context through the get-actor-output tool and the previewItems field in call-actor responses.
Boundary markers: The skill does not implement programmatic delimiters or 'ignore' instructions for the scraped data, though it mandates a 'Verify results' step (Step 6) to detect anomalies manually.
Capability inventory: Across its scripts and instructions, the skill utilizes command execution (mcpc), public data posting (gh issue), and local file access (Read, Grep, Glob).
Sanitization: No explicit sanitization or filtering is applied to the retrieved content; the skill relies on the agent following the manual verification workflow to identify malicious or incorrect data.

apify-mcpc