The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes potentially untrusted data through the $ARGUMENTS variable in SKILL.md and sub-skills/10-prevention.md. This constitutes a surface for indirect prompt injection (Category 8).
Ingestion points: User-provided data enters via $ARGUMENTS in SKILL.md and sub-skills/10-prevention.md.
Boundary markers: The skill does not employ explicit delimiters or system instructions to ignore instructions embedded within the processed issue.
Capability inventory: The skill references capabilities for code instrumentation, fix generation, and interaction with external observability platforms (e.g., DataDog, Sentry, Honeycomb).
Sanitization: No input validation or escaping of the user-provided arguments is documented in the skill instructions.
[SAFE]: The skill's primary function is to guide an agent through a structured debugging workflow. Mentions of external services like DataDog, Sentry, and New Relic are for observability purposes and are treated as well-known technology services. The code examples provided are illustrative and do not instruct the agent to execute untrusted remote code.

debugging-toolkit-smart-debug