The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python's subprocess.run to execute the Volatility3 CLI (vol) across several files including scripts/agent.py, scripts/process.py, and an embedded script in SKILL.md.
Evidence: The implementation consistently uses argument lists (e.g., cmd = [self.vol3, "-f", self.dump_path, ...]) rather than shell strings, and shell=True is not employed, which effectively prevents shell command injection vulnerabilities.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse external data (memory dump files) that may contain malicious content intended to influence the agent's behavior.
Ingestion points: Memory dump files are processed by the run_plugin and run_vol3_plugin functions in SKILL.md, scripts/agent.py, and scripts/process.py.
Boundary markers: Absent. While the skill parses JSON output from the forensics tool, it does not provide explicit instructions or delimiters to the agent to disregard potential instructions embedded within the extracted strings (such as process names or command-line arguments).
Capability inventory: The skill possesses the capability to execute shell commands (via vol) and read from the file system. These are necessary for forensics but could be targeted by an injection.
Sanitization: Absent. The scripts extract raw strings from memory (e.g., ImageFileName, Hexdump, Owner) and incorporate them directly into the JSON report provided to the agent context.

performing-memory-forensics-with-volatility3-plugins