The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill provides a Lua script template to be executed via the query_project tool. The agent is instructed to adapt the script by substituting placeholders like <target_function> and then execute the resulting code dynamically within the analysis environment.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of external binary code by decompiling it into C-like pseudocode. A malicious actor could embed prompt injection strings within the binary (e.g., in function names, strings, or code structures) that could potentially influence the agent's behavior when it reviews the output.
Ingestion points: The query_project tool returns decompiled text from binary functions into the agent's context (SKILL.md).
Boundary markers: The provided instructions do not include specific delimiters or warnings to ignore instructions found within the decompiled code.
Capability inventory: The skill utilizes the query_project tool to execute Lua queries and open_project to access binary files (SKILL.md).
Sanitization: There is no evidence of sanitization or filtering applied to the decompiled pseudocode before it is presented to the agent.

decompiler