The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requests access to the Bash tool in its frontmatter. While the provided instructions focus on report generation and signal aggregation, the availability of a shell environment increases the potential impact if the agent is manipulated by malicious data.
[SAFE]: Indirect Prompt Injection Surface. The skill is designed to ingest and process data from potentially untrusted external sources, which could contain adversarial instructions.
Ingestion points: The skill reads from signals.jsonl, monthly performance reports, and customer feedback aggregations (including review sites and social mentions).
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the ingested signal data.
Capability inventory: The skill utilizes Bash, Write, Edit, Read, Glob, and Grep tools.
Sanitization: No sanitization or validation steps are described for the signal data before it is aggregated into recommendations and briefs.
[SAFE]: No obfuscation, hardcoded credentials, persistence mechanisms, or unauthorized remote code execution patterns were detected in the skill content. All file operations are restricted to the local engagement directory structure.

continuous-improvement-loop