The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions require the agent to execute a Python script (campaign-tracker.py) with arguments derived from context variables. This script is not provided with the skill, making its operations unverifiable. Additionally, the use of a {slug} variable in the command string without explicit sanitization steps poses a risk of command injection.
[DATA_EXFILTRATION]: The skill accesses files within a hidden application directory (~/.claude-marketing/) using a path constructed with the {slug} variable. The lack of path validation or sanitization for this variable could allow for directory traversal attacks, potentially exposing sensitive files if the agent is manipulated into reading from unauthorized paths.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external configuration and guideline files without security boundaries.
Ingestion points: Reads data from ~/.claude-marketing/brands/{slug}/profile.json, _manifest.json, and associated markdown files such as restrictions.md and messaging.md.
Boundary markers: None. There are no instructions to the agent to treat this external content as untrusted or to ignore any instructions embedded within it.
Capability inventory: The skill is authorized to perform file system reads and execute subprocess commands via the campaign-tracker.py script.
Sanitization: No validation or sanitization is performed on the ingested content before it is incorporated into the agent's reasoning and output generation.

marketing-automation