The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of an external JAR file from an untrusted GitHub repository (github.com/BuffaloWill/burpsuite-project-file-parser). This source is not a verified organization or well-known service.
[COMMAND_EXECUTION]: The skill relies on executing a local Bash script (burp-search.sh) that invokes java -jar to run the third-party extension. This execution path processes sensitive project files and could be exploited if the JAR or wrapper script is compromised.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) as it ingests untrusted HTTP traffic from Burp projects.
Ingestion points: Raw HTTP headers and bodies are read from .burp files using the burp-search.sh tool.
Boundary markers: Absent. The skill lacks explicit delimiters or instructions to ignore instructions embedded within the traffic.
Capability inventory: Uses the Bash tool to execute commands and process file content.
Sanitization: Employs jq and head to truncate output and limit total bytes, which reduces but does not eliminate the risk of the agent following instructions found in the traffic.
[DATA_EXFILTRATION]: The skill accesses .burp files, which are highly sensitive as they typically contain session cookies, authentication tokens, and internal infrastructure details captured during security audits.

burpsuite-project-parser