The Agent Skills Directory

[DYNAMIC_EXECUTION]: The helper scripts scripts/create_bug_report.sh and scripts/generate_test_cases.sh contain a command injection vulnerability. The prompt_input function uses the eval command to dynamically assign user-provided input from read -r to variables. An attacker can provide input containing shell metacharacters or command substitutions (e.g., $(command)) to execute arbitrary code in the user's environment.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data from requirements and Figma URLs, creating a surface for indirect prompt injection attacks.
Ingestion points: The skill parses feature descriptions, testing requirements, and design specifications provided by the user or fetched via Figma URLs.
Boundary markers: There are no explicit delimiters or instructions defined in the skill to prevent the agent from executing instructions embedded within the ingested data.
Capability inventory: The agent can write to the filesystem via the included bash scripts and interact with external design specifications via the Figma MCP tool.
Sanitization: The skill lacks validation or sanitization mechanisms for the data it processes before generating testing documentation.

qa-test-planner