The Agent Skills Directory

[COMMAND_EXECUTION]: The skill workflow begins by executing a local shell script located at .specify/scripts/bash/check-prerequisites.sh. This script is part of the repository's internal tooling and is used to derive configuration variables for subsequent steps. Execution of shell scripts poses a risk if the script content is malicious or can be influenced by local environmental factors.
[DATA_EXFILTRATION]: The skill creates and writes to a directory FEATURE_DIR/checklists/. While this is intended for checklist generation, the capability to create directories and write files could be misused to write data to unauthorized locations on the local filesystem.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted content from local markdown files (spec.md, plan.md, tasks.md) and incorporates it into the agent's generation context.
Ingestion points: Content is read from spec.md, plan.md, and tasks.md within the dynamically determined FEATURE_DIR.
Boundary markers: The instructions do not specify the use of delimiters (such as XML tags or triple backticks) or explicit 'ignore embedded instructions' warnings when processing the content of these files.
Capability inventory: The skill possesses the ability to execute shell scripts (check-prerequisites.sh), read various project files, and write new files to the filesystem.
Sanitization: No evidence of sanitization, validation, or escaping of the ingested markdown content is present before it is used to generate the final checklist output.

speckit-checklist