The Agent Skills Directory

[PROMPT_INJECTION] (LOW): Susceptible to Indirect Prompt Injection.
Ingestion points: The skill utilizes the Read tool and Bash commands to ingest content from files within a target codebase (e.g., src/auth/).
Boundary markers: No specific delimiters or instructions are defined to warn the agent about ignoring embedded instructions within the ingested data.
Capability inventory: The skill has access to powerful tools including Bash (command execution), Read (file access), and Task (agent spawning).
Sanitization: No sanitization or validation of the content read from the codebase is performed before it is processed by the agents.
[COMMAND_EXECUTION] (SAFE): The use of the Bash tool is consistent with the skill's purpose.
The provided documentation and templates focus on searching and exploring codebases. No malicious command strings, obfuscated code, or unauthorized network operations were detected.

Spawn Swarm