The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from the web and external source code repositories.
Ingestion points: Web search results and cloned repository content (README.md, code examples) mentioned in the research process in SKILL.md.
Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded instructions within the processed data.
Capability inventory: The skill utilizes shell commands including git clone, mkdir, and cat to manage data in /tmp and ./scratch/research/ (found in SKILL.md).
Sanitization: Absent. The skill does not specify any validation or filtering of the retrieved external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill fetches external content from a well-known service for technical examination.
Evidence: Clones repositories using git clone https://github.com/owner/repo.git in SKILL.md.
[COMMAND_EXECUTION]: The skill executes shell commands to perform file system operations and data inspection.
Evidence: Uses mkdir -p ./scratch/research, cd /tmp, and cat /tmp/repo/README.md in SKILL.md.

research