The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions in SKILL.md direct the agent to execute shell commands like cat and python scripts/fetch_skill.py to retrieve data from local or remote sources. While intended for skill comparison, this capability could be abused if the agent is directed to access sensitive files.
[EXTERNAL_DOWNLOADS]: The scripts/fetch_skill.py utility uses urllib.request to download content from arbitrary URLs provided by the user, which can lead to the ingestion of malicious data.
[PROMPT_INJECTION]: The skill's core function is to analyze untrusted content from external sources, making it vulnerable to indirect prompt injection.
Ingestion points: Data enters the agent context through URLs and local file paths processed by scripts/fetch_skill.py and cat in SKILL.md.
Boundary markers: There are no delimiters or instructions to ignore embedded commands within the fetched content.
Capability inventory: The skill can execute shell commands (cat) and Python scripts (scripts/fetch_skill.py) to access the filesystem as described in SKILL.md.
Sanitization: The skill performs no sanitization, escaping, or validation of the external content before it is processed by the agent.

skill-comparison