The Agent Skills Directory

[SAFE]: The skill is a collection of instructional markdown files providing a workflow for bug reporting. No executable code, scripts, or malicious prompt patterns were identified across the skill definition and reference files.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection as it involves reading and processing external data from Jira issues which could be controlled by untrusted third parties. However, the risk is effectively managed through procedural controls defined in the instructions.
Ingestion points: Processes existing Jira issues, descriptions, and comments retrieved via search/read tools as described in SKILL.md and references/context-search.md.
Boundary markers: The skill explicitly mandates that the agent must present search results to the user and obtain deliberate approval before taking any automated actions, such as creating new tickets.
Capability inventory: Involves reading Jira data and potentially invoking mcp-atlassian_jira_create_issue for ticket creation.
Sanitization: references/pitfalls.md (Pitfall 8) explicitly instructs the agent to redact secrets, authorization tokens, and personally identifiable information (PII) before including content in a bug report.

write-bug