The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from an external issue tracker.
Ingestion points: The skill fetches and reads the full body and comments of issues from a project issue tracker (SKILL.md, Step 1).
Boundary markers: There are no explicit instructions or delimiters used to isolate external issue content from the agent's internal instructions.
Capability inventory: The agent can perform codebase exploration and execute commands via the bd (Beads) tool to create issues and manage task dependencies.
Sanitization: There is no evidence of sanitization or validation of the text fetched from the issue tracker before it is processed by the agent.
[COMMAND_EXECUTION]: The skill uses the bd (Beads) CLI tool to perform issue management tasks.
Evidence: The skill instructs the agent to use bd create and bd dep add to publish issues and record dependencies.
Context: These commands are part of the core functionality for interacting with the project's issue tracker and do not appear to involve arbitrary command injection or suspicious execution patterns.

to-issues