The Agent Skills Directory

[SAFE]: The skill utilizes authorized tool calls to SE Ranking and Planable MCPs to perform its tasks. There are no signs of malicious code, unauthorized network requests, or credential theft.
[SAFE]: Includes a dedicated 'Connector health check' section that instructs the agent to verify authentication and connectivity with external services before executing commands, preventing errors and ensuring a secure environment.
[SAFE]: Demonstrates awareness of resource limits and stability by providing instructions on how to handle large JSON responses from SEO tools (e.g., using specific query parameters or filtering tools like jq).
[PROMPT_INJECTION]: The skill's architecture creates a surface for indirect prompt injection as it processes external rankings and competitor data to generate social media content drafts.
Ingestion points: External SEO data and competitor information are retrieved using SE Ranking tool calls as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from obeying commands potentially embedded in the fetched SEO data.
Capability inventory: The skill allows the creation and labeling of social media posts in Planable (e.g., create_post, create_grouped_post) as outlined in SKILL.md.
Sanitization: No specific data validation or sanitization steps are provided for the content retrieved from external sources before it is used in the creation of social media posts.

local-gmb-visibility