The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a bash command python3 ${CLAUDE_PLUGIN_ROOT}/scripts/graph_query.py --action search --query "<term>" --limit 20 where the <term> variable is taken directly from user input. This shell interpolation pattern is highly susceptible to command injection attacks if the input contains shell metacharacters such as backticks, semicolons, or command substitution sequences.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the local filesystem and code knowledge graph which may contain untrusted content.
Ingestion points: Results from graph_query.py and the contents of source files read in Step 4.
Boundary markers: No delimiters or ignore instructions are used to wrap the ingested content.
Capability inventory: The skill has shell command execution capabilities via bash.
Sanitization: There is no evidence of sanitization, filtering, or escaping of the data retrieved from the codebase before it is processed by the agent.

graph-search