The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to dynamically create a shell script (count_instructions.sh) on the local file system and execute it using chmod +x to count lines in agent configuration files.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted content from user-provided project directories.
Ingestion points: The agent reads data from YAML configuration files in agents/ and connections/, as well as docstrings and code from Python files in tools/.
Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the content of these files as untrusted or to ignore embedded instructions within them.
Capability inventory: The skill allows the agent to read files, generate shell scripts, and perform command-line execution.
Sanitization: The analysis process does not include steps for sanitizing, escaping, or validating the input data before summarizing it into documentation reports.

wxo-analyzer