The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests potentially untrusted data from the local codebase to inform ticket generation, creating a surface for indirect prompt injection.
Ingestion points: The skill researches project files including README.md, CLAUDE.md, AGENTS.md, source files, and existing tickets in directories like .tickets/ or docs/tickets/ (identified in SKILL.md, Step 2).
Boundary markers: The skill does not implement specific delimiters or instructions to ignore embedded commands within the ingested codebase files before they are processed by sub-agents.
Capability inventory: The skill utilizes file-system exploration (Glob, Grep) and spawns parallel sub-agents to summarize findings.
Sanitization: The instructions do not specify sanitization or validation of the content read from files before it is interpolated into agent prompts.
[EXTERNAL_DOWNLOADS]: The skill provides installation instructions that reference an external source for skill management.
Evidence: The README.md file suggests installation via npx skills add from the author's GitHub repository (https://github.com/belsrc/skills).

ticket-creator