The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data (binary code and pseudocode) which can contain malicious instructions intended to influence the agent's behavior during analysis.
Ingestion points: The skill uses procedure_pseudo_code and procedure_assembly to read binary content into the agent's context (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat findings within the binary as data rather than instructions, nor are there warnings to ignore embedded commands.
Capability inventory: The agent has the ability to modify the project state via rename_function and add_note based on its interpretation of the ingested code.
Sanitization: The instructions do not include any steps for sanitizing or validating strings, comments, or symbols extracted from the binary before they are processed by the LLM.

name-functions