The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts to manage marketing data. Evidence includes calls to python campaign-tracker.py for listing campaigns in SKILL.md and python scripts/benchmark_book.py for recording and quoting benchmark data in competitive-intelligence.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from brand profiles and guidelines, creating an opportunity for indirect prompt injection if these files contain malicious instructions.
Ingestion points: The agent reads brand context from ~/.claude-marketing/brands/{slug}/profile.json and manifest files within the brand's directory as specified in SKILL.md.
Boundary markers: There are no explicit delimiters or system instructions provided to ensure the agent treats the content of these files as data rather than instructions.
Capability inventory: The skill possesses the capability to read files from the user's home directory and execute shell commands through the mentioned Python scripts.
Sanitization: The analysis found no evidence of sanitization, filtering, or validation routines applied to the ingested brand profile data before it is incorporated into the agent's context.

analytics-insights