The Agent Skills Directory

[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill provides instructions to install the uv package manager using a remote script from astral.sh (curl -LsSf https://astral.sh/uv/install.sh | sh). This source is a well-known provider for this tool.
[PRIVILEGE_ESCALATION]: The skill includes commands to manage system services via sudo systemctl and terminate conflicting processes using kill to resolve port occupancy during local development sessions.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data by reading agent execution traces and CloudWatch logs.
Ingestion points: Fetches recent logs and execution traces via agentcore traces get, agentcore logs, and aws logs tail (SKILL.md, Step 3 and 4).
Boundary markers: No explicit instructions are provided to the agent to disregard instructions that might be embedded within the log data being parsed.
Capability inventory: The skill utilizes Bash, Read, Grep, and Glob tools to interact with the environment and analyze logs.
Sanitization: There is no explicit sanitization of log content before it is presented to or processed by the agent.

agents-debug