The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines workflows for ingesting and analyzing external Solidity source code. This introduces a potential surface for indirect prompt injection, where an attacker could place malicious instructions within code comments or string literals in a smart contract. If an agent processes the analysis results or the raw code, it might inadvertently follow these instructions.
Ingestion points: The skill instructions in references/core-config.md describe how the tool identifies and reads Solidity files within a workspace.
Capability inventory: The tool executes static analysis via the aderyn CLI and produces reports in Markdown, JSON, and SARIF formats, as detailed in references/core-report-formats.md.
Boundary markers: The instructions do not specify the use of clear delimiters or instructions for the agent to disregard natural language commands found within the target source code.
Sanitization: There are no explicit requirements or steps for sanitizing the analyzed code or the generated report content for potential injection patterns before it is presented to the agent's context.

aderyn