The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the pyzotero package and its CLI components from standard, well-known registries like PyPI.
[CREDENTIALS_UNSAFE]: The documentation includes placeholder credentials (e.g., 'ABC1234XYZ') for instructional purposes and correctly advises users to manage sensitive API keys via environment variables or .env files.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external bibliographic libraries, including item titles, notes, and full-text PDF content, which constitutes a surface for indirect prompt injection.
Ingestion points: Data enters the context via zot.items(), zot.everything(), and zot.fulltext_item() as described in references/read-api.md and references/full-text.md.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the retrieved bibliographic data.
Capability inventory: The skill has access to powerful tools including Bash, Write, and Edit as specified in SKILL.md.
Sanitization: There is no mention of sanitization, escaping, or validation of the content retrieved from the Zotero API before it is processed by the agent.

pyzotero