cy-execute-task
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates a vulnerability surface.
- Ingestion points: The skill reads task specification markdown, PRD documents (including
_techspec.mdand_tasks.md), and ADRs from theadrs/directory. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat content within these documents as untrusted or to ignore embedded instructions.
- Capability inventory: The skill is capable of executing shell commands (validation commands), writing to the file system (updating task files and memory), and performing local git commits.
- Sanitization: No sanitization or validation of the content within the ingested markdown files is performed before they influence the agent's actions.
- [DYNAMIC_EXECUTION]: In Step 4 of the workflow, the skill instructs the agent to "Run every test and validation command listed in the task specification." This facilitates the execution of arbitrary commands defined within input data, which could lead to command injection if the task specification is sourced from an untrusted party.
- [COMMAND_EXECUTION]: The skill performs several automated file system and version control operations, including modifying tracking files and creating local git commits based on the processed task data.
Audit Metadata