The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses pnpx ctx7@latest, which fetches the latest version of the ctx7 package from the NPM registry during execution.
[REMOTE_CODE_EXECUTION]: By using pnpx to run a package from a public registry, the skill executes remote code on the local system. The use of the @latest tag ensures the most recent version is downloaded, which can be a risk if the package is compromised or subject to a supply chain attack.
[COMMAND_EXECUTION]: The skill requires direct execution of shell commands (ctx7 library, ctx7 docs, ctx7 login) and environment variable manipulation (export CONTEXT7_API_KEY=...) to function.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external documentation service.
Ingestion points: Data enters the context via the output of ctx7 library and ctx7 docs commands (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the documentation output as untrusted data or to ignore instructions contained within it.
Capability inventory: The skill possesses shell execution capabilities through pnpx and ctx7 (SKILL.md).
Sanitization: No sanitization or validation of the documentation content is performed before it is presented to the agent's context.

find-docs