The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl and jq commands to interact with the Paperless-ngx REST API for searching, listing correspondents, and fetching document content. These operations are essential for the skill's intended functionality.
[SAFE]: The skill manages its configuration (API URL and token) in ~/.config/paperless-search/config.json. This is a dedicated path for the skill and follows standard practices for local credential storage without accessing generic sensitive system files.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it fetches raw document content from an external API (/api/documents/{id}/). Malicious text within stored documents could potentially influence agent behavior.
Ingestion points: SKILL.md (API examples fetching document content via curl)
Boundary markers: Absent; the instructions do not use delimiters to wrap retrieved document content
Capability inventory: Shell command execution (curl, jq), directory management (mkdir), and file writing (cat) specified in SKILL.md
Sanitization: Absent; no instructions are provided to sanitize or validate the content retrieved from the document archive before it is processed by the agent

paperless-search