The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not include any executable scripts or hidden code. Its logic is transparent and focused on the stated purpose of technical review.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze untrusted external data such as source code and pull requests. However, this is inherent to its function as a review tool.
Ingestion points: Reads external files and codebases using the Read, Grep, and Glob tools.
Boundary markers: Absent. The skill does not specify the use of delimiters or 'ignore' instructions for the content being reviewed.
Capability inventory: The skill has access to powerful tools including Bash, Read, and Agent to perform its analysis.
Sanitization: No explicit sanitization or validation of the input content is defined in the instructions.

swing-review