The Agent Skills Directory

[SAFE]: The skill is a well-structured security tool for detecting Server-Side Template Injection (SSTI). It defines a clear reconnaissance and taint analysis methodology for agents to follow when auditing codebases.
[PROMPT_INJECTION]: The skill inherently processes untrusted external data (the codebase being analyzed), which presents a potential surface for indirect prompt injection if the source code contains malicious instructions intended to influence the agent. However, the skill provides highly specific pattern-matching instructions and a structured output format, which significantly mitigates this risk.
Ingestion points: The agent reads source code files from the user's repository during the reconnaissance and verification phases.
Boundary markers: Absent; the instructions do not explicitly mandate delimiters or provide warnings to ignore natural language instructions found within the code comments or strings.
Capability inventory: The skill performs file system read and write operations within the project directory to store intermediate findings and final results.
Sanitization: Absent; the tool operates on raw source code to perform its analysis.

sast-ssti