The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx -y godpowers@7 in several steps to download and execute a specific version of a package from the public npm registry. This occurs automatically during status checks and verification steps.
[COMMAND_EXECUTION]: The skill instructs the agent to run shell commands, specifically npx -y godpowers@7 status and npx -y godpowers@7 verify "<verify command>". The latter involves executing a verification command that may be dynamically determined by the agent based on the project context.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of local project files.
Ingestion points: The skill reads the contents of .godpowers/STATE.md to determine the current stage of a project and choose the next steps (SKILL.md, Step 1 and 3).
Boundary markers: There are no boundary markers or instructions to treat the content of the state file as untrusted data.
Capability inventory: The skill has the capability to execute shell commands via npx and modify the local filesystem (touch STATE.md).
Sanitization: There is no evidence of sanitization or validation of the goal or requirements read from the state file before they are used to influence the agent's logic or the arguments passed to the verification command.

god