The Agent Skills Directory

[SAFE]: The skill provides instructional content and SQL query templates for reverse engineering binaries within the IDA Pro environment. It does not perform any network operations, access sensitive system files, or execute untrusted code. All described operations are local to the researcher's analysis environment.
[PROMPT_INJECTION]: Indirect Prompt Injection Surface:
Ingestion points: Binary data and metadata (symbols, strings) ingested via SQL queries (e.g., SELECT decompile, SELECT ... FROM ctree) in SKILL.md.
Boundary markers: None present in the provided templates.
Capability inventory: Uses Bash, Read, Glob, and Grep tools, and allows database modifications via SQL UPDATE and INSERT commands in SKILL.md.
Sanitization: No explicit sanitization or validation of the data retrieved from the binary is performed before processing.

re-source