The Agent Skills Directory

[DYNAMIC_EXECUTION]: The utility script scripts/patch_wikilink.py contains an exec() call within its self_test function. This function is designed to verify that the script's code transformation logic produces valid Python code. The execution is performed on a hardcoded test string defined within the script itself.\n- [COMMAND_EXECUTION]: The instructions direct the agent to perform software installation tasks using pip and npx. Additionally, the skill utilizes a Python script to perform in-place modifications of the graphifyy library's source files in the local environment to resolve a known link-generation issue.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data which creates an attack surface for indirect prompt injection.\n
Ingestion points: Untrusted data enters the agent context via graphify update on a codebase and graphify add for external URLs (referenced in SKILL.md and references/cli-command-map.md).\n
Boundary markers: No explicit delimiters or instructions to ignore embedded content were found in the skill instructions.\n
Capability inventory: The agent has access to Bash, Read, Write, Grep, and Glob tools, as well as the ability to execute the graphify CLI.\n
Sanitization: No sanitization or filtering of the ingested content is specified before it is processed by the graph extraction logic.

graphify