The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple external sources which could contain malicious instructions designed to influence the implementation plan or code generation.
Ingestion points: Linear issue titles and descriptions, GitHub pull request comments, Sentry error details, and Obsidian vault notes.
Boundary markers: There are no explicit instructions in the skill to use delimiters or specific ignore-embedded-instructions warnings when processing this external content.
Capability inventory: The skill has significant capabilities including shell command execution (git, gh, bundle exec, bin/lint), code implementation through specialized sub-skills, and automated pull request creation.
Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from external APIs before it is used to generate implementation tasks.
[COMMAND_EXECUTION]: The skill uses metadata from a remote service to construct shell commands. Specifically, in Step 4, it uses the branchName field from a Linear issue to execute git checkout -b "$BRANCH_NAME". While the variable is quoted in the instruction, which mitigates simple space-separated injections, using externally-controlled strings in shell commands represents a potential attack surface for argument injection if not strictly validated by the platform.
[SAFE]: The skill demonstrates security awareness by using quoted heredocs (cat <<'EOF') for git commit messages and pull request bodies. This prevents the shell from performing variable expansion or command substitution on the content of the messages, effectively neutralizing injection risks from those specific data flows.

linear-implement