The Agent Skills Directory

[SAFE]: The skill uses a transparent, template-based process for generating specifications and does not exhibit any obfuscation, base64 encoding, or hidden command patterns.
[SAFE]: No hardcoded credentials, sensitive file paths (e.g., .ssh, .env), or unauthorized network operations were detected in the skill's definition or referenced setup command.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its data processing and publishing workflow.
Ingestion points: The skill reads the current conversation context and performs an exploration of the project's codebase to gather information (SKILL.md).
Boundary markers: Absent. The instructions do not specify delimiters or provide warnings to the agent to ignore instructions that might be embedded within the project files or conversation history.
Capability inventory: The skill has the capability to publish the synthesized results to the project issue tracker and apply triage labels.
Sanitization: Absent. There is no logic or instruction provided to sanitize, filter, or escape the content ingested from the codebase or conversation before it is published to the issue tracker.

to-spec