The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The discovery script scripts/discover_promo_system.py is designed to search through .env files, which are listed as sensitive file paths. The script identifies lines matching promo-related keywords and prints up to 100 characters of the content, potentially exposing sensitive environment variables or secrets to the agent's output context.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it ingests untrusted data from the user's project files during the discovery phase without sufficient safeguards.\n
Ingestion points: The scripts/discover_promo_system.py script reads the content of all files matching specific extensions in the provided project directory.\n
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its operational instructions and the potentially malicious data contained in the files being analyzed.\n
Capability inventory: The skill allows the agent to read project files, execute local Python scripts, and write new code and documentation to the file system.\n
Sanitization: The skill does not implement sanitization or validation for the content read from external project files before it is processed by the agent.

promo-code-system