The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from various project files which may contain untrusted content.
Ingestion points: The skill reads from production/sprints/*.md, production/sprint-status.yaml, and production/epics/**/story-*.md in SKILL.md.
Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore embedded instructions within these data sources.
Capability inventory: The skill utilizes Bash (for specific script execution), Grep, Glob, and Read capabilities.
Sanitization: No sanitization or validation of the input content is performed before the model processes the data.
[DYNAMIC_CONTEXT_INJECTION]: The skill uses platform-specific !bash syntax to execute commands at load time.
Evidence: The skill executes ${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh and ${CLAUDE_SKILL_DIR}/../../scripts/story-status.sh to initialize configuration and status reporting.
Context: These injections are used for benign internal project management tasks and do not involve user-controlled input or network operations at the time of execution.
[COMMAND_EXECUTION]: The skill invokes local shell scripts and tools to aggregate project data.
Evidence: It executes a grep command with a complex regular expression to scan for update timestamps across all story files in the production/epics/ directory.
Evidence: The skill calls local scripts yaml-helper.sh and story-status.sh as permitted by the frontmatter configuration.

sprint-status