The Agent Skills Directory

[COMMAND_EXECUTION]: The SKILL.md file executes a bash script using the interpolation ${ARGUMENTS:-4.14.0}. Because these arguments are passed directly to the shell without quoting or sanitization, a malicious user could provide input containing shell metacharacters (e.g., ;, &&, ||, or backticks) to execute arbitrary commands on the system.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by fetching and processing data from external sources, including Apache Camel release pages and Maven repositories. While the sources are reputable, the script lacks sanitization for the fetched XML and HTML content before generating the AsciiDoc matrix that is subsequently displayed to the agent.
Ingestion points: The scripts/camel-springboot-matrix.sh script fetches content from camel.apache.org, repo.maven.apache.org, and Spring Boot starter repositories.
Boundary markers: None present in the generated output to delineate external data.
Capability inventory: The skill possesses capabilities for network requests (curl), file system writes (mkdir, echo to target/), and shell command execution.
Sanitization: The script uses grep, sed, and awk for extraction but does not perform validation or escaping of the values before inclusion in the final AsciiDoc file.

camel-matrix