The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to interact with the environment, specifically executing GitHub CLI commands (gh pr view, gh pr diff) during the review process. The use of a shell-access tool represents a significant capability that could be misused if the agent is compromised by external data.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. Ingestion points: Untrusted data enters the context through GitHub PR diffs, issues, and associated comments. Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore potentially malicious embedded commands within the external content. Capability inventory: The skill has access to Bash, Write, Read, Grep, and Glob tools across multiple files. Sanitization: There is no evidence of content sanitization or validation performed on the external data before it is integrated into the architectural analysis or review workflow.

software-architect