The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute the money CLI tool and npm build scripts within local workspace directories. It also supports dynamic loading of additional modules via the MONEYCLI_PROVIDER_MODULES environment variable, which allows the execution of code from arbitrary file paths.
[DATA_EXFILTRATION]: The skill accesses sensitive financial information, including session cookies stored in .cookies/moneyforward.com.cookie.json and local cache files. While this is necessary for the skill's primary function of managing financial snapshots, the handling of these credentials represents a potential data exposure risk if the agent's context is compromised.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external financial providers.
Ingestion points: Output from the money command and provider data files mentioned in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the prompt templates.
Capability inventory: The skill can execute subprocesses (money, npm) and access the file system (cookies, cache), which could be leveraged if malicious instructions are processed.
Sanitization: No explicit sanitization or validation of the ingested financial data is described.
[EXTERNAL_DOWNLOADS]: The documentation suggests installing the @yuiseki/moneycli package from a public registry. This is a vendor-owned resource matching the skill author's identity.

money