The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze project descriptions and requirements documents, which are untrusted external inputs.
Ingestion points: Project descriptions and requirements documents are processed at runtime to generate estimates as described in SKILL.md.
Boundary markers: There are no defined boundary markers or instructions to the agent to disregard instructions embedded within the analyzed project documents.
Capability inventory: The skill possesses the capability to generate and execute shell scripts that perform network requests via curl across various files including SKILL.md.
Sanitization: No content sanitization or validation logic is specified for the ingested document data.
[COMMAND_EXECUTION]: The skill provides and encourages the generation of bash scripts that use curl to interact with the Jira REST API, which involves executing shell commands with user-supplied parameters.
[CREDENTIALS_UNSAFE]: The skill instructions direct the agent to ask users for their Jira email and API tokens to be used as variables in shell commands (SKILL.md). This handling of sensitive credentials in command-line arguments can lead to exposure in shell history or process logs.

project-estimation