The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to run pandoc for document conversion. The command template provided, pandoc "FOLDER/tmp.md" -o "FOLDER/{original-filename}-review.doc", directly interpolates the manuscript's filename. If a manuscript has a malicious filename containing shell metacharacters (e.g., ;, &&, or backticks), it could lead to arbitrary command execution when the conversion step is triggered.
[PROMPT_INJECTION]: The skill processes untrusted manuscripts and supporting files, making it vulnerable to indirect prompt injection where an attacker embeds instructions within a paper to manipulate the agent's behavior.
Ingestion points: Reads manuscript files (main.tex, *.pdf) and secondary .tex files in subfolders using the Read and Glob tools.
Boundary markers: Absent. The instructions do not specify any delimiters or warnings for the agent to ignore instructions embedded within the processed text.
Capability inventory: The skill has access to powerful tools including Bash, Write, and Read, which could be exploited if an injection attack is successful.
Sanitization: None. The skill does not perform any validation or filtering of the text extracted from the manuscript before using it to generate the report and editor letter.

referee-report