KSeF Accounting Agent

Specialized knowledge for operating the National e-Invoice System (KSeF) in the KSeF 2.0 environment with the FA(3) structure. Supports accounting tasks related to electronic invoicing in Poland.

Security Model

This skill is instruction-only — it consists of Markdown files containing domain knowledge, architectural patterns and code examples. It does not contain any executable code, binaries, installation scripts or runtime dependencies.

Skill-side guarantees:

• disableModelInvocation: true / disable-model-invocation: true — declared in both the frontmatter metadata (both formats: camelCase and kebab-case) and in the dedicated manifest skill.json. The skill should not be invoked autonomously by the model.
• secret: true — the environment variables KSEF_TOKEN and KSEF_ENCRYPTION_KEY are marked as secrets in the frontmatter and skill.json, signaling to the platform that they must be isolated and must not be logged or displayed.
• No executable code — all examples (Python, XML, JSON) are illustrative, NOT code executed by the skill.
• No installation — the skill does not write files to disk, does not download dependencies, does not modify system configuration.
• Dedicated manifest skill.json — a machine-readable file with security metadata, environment variable declarations and constraints. If the platform does not parse the SKILL.md frontmatter correctly, it should read metadata from skill.json.

NOTE — registry metadata verification before installation:

Security flags are declared in two sources: the SKILL.md frontmatter and skill.json. Nevertheless, the hosting platform may not read or enforce these flags. Before installation you MUST perform the following steps:

1. Check registry metadata — after adding the skill to the platform, open the registry metadata view displayed by the platform. Verify that the disable-model-invocation field is set to true and that the environment variables (KSEF_TOKEN, KSEF_ENCRYPTION_KEY, KSEF_BASE_URL) are visible with the secret label. If the platform shows not set, false or does not display these fields — the flags are NOT enforced.
2. If registry metadata does not match frontmatter/skill.json — treat the skill as higher risk: DO NOT provide credentials (tokens, certificates, keys), DO NOT configure environment variables (KSEF_TOKEN, KSEF_ENCRYPTION_KEY), DO NOT allow autonomous use.
3. Verify environment variable isolation — confirm that the platform isolates env vars and does not log/display their values in the conversation.
4. If the platform does not enforce flags — contact the platform provider to enable support for disableModelInvocation (or parsing of skill.json) or do not install the skill with access to any credentials.