The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill is designed to fetch and process external library documentation using the mcp__context7__get-library-docs tool. This creates an ingestion surface for untrusted data from the web.
Ingestion points: External library documentation fetched via mcp__context7__get-library-docs (SKILL.md).
Boundary markers: None explicitly defined to separate documentation content from agent instructions.
Capability inventory: The skill has access to Bash (*) and Write tools, which could be exploited if an attacker embeds instructions in public documentation (SKILL.md).
Sanitization: No sanitization or validation of the fetched documentation content is mentioned.
[Command Execution] (LOW): The skill requests Bash (*) permissions in the allowed-tools metadata. While no specific malicious scripts are included in the skill itself, the wildcard access allows for arbitrary command execution which should be restricted to the minimum necessary scope (SKILL.md).

context7