The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata. No scripts, binaries, or other executable files are provided in the skill package.
[SAFE]: The skill logic describes reading brand configuration files from the ~/.claude-marketing/ directory. These operations are scoped to the application's own context and do not involve access to sensitive system credentials or unauthorized file paths.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external data from user-provided crisis descriptions and brand profiles. While it lacks explicit boundary markers or sanitization for this untrusted input, the risk is safe because the skill's capabilities are restricted to drafting text responses, with no access to shell commands, file writing, or network operations.

crisis-response