The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a shell command python scripts/generate_schematic.py "your diagram description" using user-provided natural language as a positional argument. Since the script's source code is not provided in the skill package, it is impossible to verify if it properly sanitizes input to prevent command injection from malicious strings provided by a user or an attacker.
[PROMPT_INJECTION]: This skill possesses an attack surface for indirect prompt injection as its primary function involves processing external, untrusted data. (1) Ingestion points: The skill analyzes research methodology, scientific papers, and claims from external sources (SKILL.md). (2) Boundary markers: No delimiters or protective instructions are used to separate ingested content from the system prompt. (3) Capability inventory: The skill is configured with powerful tools including Bash, Write, and Edit, which could be exploited if the agent follows malicious instructions hidden in a scientific paper. (4) Sanitization: There are no instructions or mechanisms for sanitizing the external data before it is processed.
[NO_CODE]: The core script for generating diagrams, scripts/generate_schematic.py, is missing from the skill files despite being referenced as a primary component for visual enhancement. This makes the skill's actual operational behavior and security posture unverifiable.

alterlab-scientific-thinking