The Agent Skills Directory

[COMMAND_EXECUTION]: The bash scripts scripts/create_bug_report.sh and scripts/generate_test_cases.sh contain a command injection vulnerability. The prompt_input function uses eval to assign user-provided input to internal variables without sanitization or escaping.
Evidence: The line eval "$var_name=\"$input\"" in both scripts is vulnerable. If the $input variable contains shell metacharacters such as backticks or the $(...) syntax, the shell will execute those commands in the context of the script.
Impact: This allows any data processed by these scripts to potentially trigger arbitrary code execution on the user's system.
[PROMPT_INJECTION]: The skill exhibits a significant surface for indirect prompt injection because it ingests untrusted data and passes it to the vulnerable eval command.
Ingestion points: User-supplied text for bug descriptions, titles, and test steps in scripts/create_bug_report.sh and scripts/generate_test_cases.sh.
Boundary markers: Absent. There are no delimiters or instructions to treat the input as data only.
Capability inventory: The skill can execute shell commands via the vulnerable scripts and write files to the local directory.
Sanitization: Absent. The scripts perform no validation or escaping of the input before processing it with eval.

qa-test-planner