The Agent Skills Directory

[COMMAND_EXECUTION]: The skill workflow includes the use of shell commands to browse and read project files. Evidence: Step 1 of the workflow process instructs the agent to run cat ai/memory-bank/brand-guidelines.md, ls public/images/brand/, and grep -i "story\|narrative\|message" ai/memory-bank/*.md.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external files that could contain untrusted instructions. Evidence Chain: 1. Ingestion points: Markdown files in ai/memory-bank/ and images in public/images/brand/. 2. Boundary markers: Absent; there are no instructions provided to the agent to delimit or ignore instructions embedded within the processed content. 3. Capability inventory: Shell command execution via cat, ls, and grep. 4. Sanitization: Absent; the skill processes data from these files directly without filtering or validation.

visual-storyteller